{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/exploration-by-random-network-distillation","title":"Exploration by Random Network Distillation","arxiv_id":"1810.12894","date":"2018-10-30","proceeding":"ICLR 2019","authors":["Yuri Burda","Harrison Edwards","Amos Storkey","Oleg Klimov"],"abstract":"We introduce an exploration bonus for deep reinforcement learning methods\nthat is easy to implement and adds minimal overhead to the computation\nperformed. The bonus is the error of a neural network predicting features of\nthe observations given by a fixed randomly initialized neural network. We also\nintroduce a method to flexibly combine intrinsic and extrinsic rewards. We find\nthat the random network distillation (RND) bonus combined with this increased\nflexibility enables significant progress on several hard exploration Atari\ngames. In particular we establish state of the art performance on Montezuma's\nRevenge, a game famously difficult for deep reinforcement learning methods. To\nthe best of our knowledge, this is the first method that achieves better than\naverage human performance on this game without using demonstrations or having\naccess to the underlying state of the game, and occasionally completes the\nfirst level.","url_abs":"http://arxiv.org/abs/1810.12894v1","url_pdf":"http://arxiv.org/pdf/1810.12894v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"exploration-by-random-network-distillation","repo_url":"https://github.com/openai/random-network-distillation","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"exploration-by-random-network-distillation","repo_url":"https://github.com/DuaneNielsen/rnd","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"exploration-by-random-network-distillation","repo_url":"https://github.com/Francesco-Sovrano/Combining--experience-replay--with--exploration-by-random-network-distillation-","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"exploration-by-random-network-distillation","repo_url":"https://github.com/Justkim/random-network-distillation-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"exploration-by-random-network-distillation","repo_url":"https://github.com/LeejwUniverse/RL_Exploration_Pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"exploration-by-random-network-distillation","repo_url":"https://github.com/Narsil/rl-baselines","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"exploration-by-random-network-distillation","repo_url":"https://github.com/alirezakazemipour/ppo-rnd","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"exploration-by-random-network-distillation","repo_url":"https://github.com/bacdavid/RND-O","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"exploration-by-random-network-distillation","repo_url":"https://github.com/balloch/rl-exploration-transfer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"exploration-by-random-network-distillation","repo_url":"https://github.com/forevergj/multithreading_ppo_RND","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"exploration-by-random-network-distillation","repo_url":"https://github.com/jakegrigsby/supersonic","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"exploration-by-random-network-distillation","repo_url":"https://github.com/jcwleo/random-network-distillation-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"exploration-by-random-network-distillation","repo_url":"https://github.com/jhare96/reinforcement-learning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"exploration-by-random-network-distillation","repo_url":"https://github.com/kngwyu/intrinsic-rewards","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"exploration-by-random-network-distillation","repo_url":"https://github.com/lgerrets/rl18-curiosity","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"exploration-by-random-network-distillation","repo_url":"https://github.com/michalnand/reinforcement_learning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"exploration-by-random-network-distillation","repo_url":"https://github.com/microsoft/strategically_efficient_rl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"exploration-by-random-network-distillation","repo_url":"https://github.com/riveSunder/carle","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"exploration-by-random-network-distillation","repo_url":"https://github.com/riveSunder/moving_in_morley","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"exploration-by-random-network-distillation","repo_url":"https://github.com/rle-foundation/rlexplore","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"jax","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"exploration-by-random-network-distillation","repo_url":"https://github.com/uoe-agents/derl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"exploration-by-random-network-distillation","repo_url":"https://github.com/opendilab/DI-engine/blob/main/ding/reward_model/rnd_reward_model.py","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"atari-games","task_name":"Atari Games"},{"task_slug":"deep-reinforcement-learning","task_name":"Deep Reinforcement Learning"},{"task_slug":"montezumas-revenge","task_name":"Montezuma's Revenge"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"unsupervised-reinforcement-learning","task_name":"Unsupervised Reinforcement Learning"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/atari-games-on-atari-2600-gravitar","task":"Atari Games","dataset":"Atari 2600 Gravitar","model":"RND","rank_in_archive_order":11,"of":53,"metrics":{"Score":"3906"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-montezumas-revenge","task":"Atari Games","dataset":"Atari 2600 Montezuma's Revenge","model":"RND","rank_in_archive_order":5,"of":50,"metrics":{"Score":"8152"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-pitfall","task":"Atari Games","dataset":"Atari 2600 Pitfall!","model":"RND","rank_in_archive_order":20,"of":23,"metrics":{"Score":"-3"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-private-eye","task":"Atari Games","dataset":"Atari 2600 Private Eye","model":"RND","rank_in_archive_order":11,"of":52,"metrics":{"Score":"8666"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-solaris","task":"Atari Games","dataset":"Atari 2600 Solaris","model":"RND","rank_in_archive_order":17,"of":23,"metrics":{"Score":"3282"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-venture","task":"Atari Games","dataset":"Atari 2600 Venture","model":"RND","rank_in_archive_order":9,"of":55,"metrics":{"Score":"1859"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1810.12894","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1810.12894"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/openai/random-network-distillation","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/kngwyu/intrinsic-rewards","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/michalnand/reinforcement_learning","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/LeejwUniverse/RL_Exploration_Pytorch","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/bacdavid/RND-O","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/rle-foundation/rlexplore","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/lgerrets/rl18-curiosity","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/riveSunder/carle","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/alirezakazemipour/ppo-rnd","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/balloch/rl-exploration-transfer","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/opendilab/DI-engine/blob/main/ding/reward_model/rnd_reward_model.py","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Justkim/random-network-distillation-pytorch","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jakegrigsby/supersonic","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/forevergj/multithreading_ppo_RND","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jhare96/reinforcement-learning","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/DuaneNielsen/rnd","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Narsil/rl-baselines","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jcwleo/random-network-distillation-pytorch","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Francesco-Sovrano/Combining--experience-replay--with--exploration-by-random-network-distillation-","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/riveSunder/moving_in_morley","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/uoe-agents/derl","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/microsoft/strategically_efficient_rl","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":16,"ran_fixture":1,"ran_draft_wrong":6,"ran_honours":2,"ran_violates":1,"unverified":17},"by_repo_kind":{"listed":{"samples":43,"ran":26,"repositories":14}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":15,"samples":[{"code_sha256_prefix":"618895158b828fd1","entry":"ActionEmbedding","repo":"DuaneNielsen/rnd","repo_kind":"listed","path":"novelty_policy.py","file_url":"https://github.com/DuaneNielsen/rnd/blob/HEAD/novelty_policy.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"618895158b828fd1"}},{"code_sha256_prefix":"ab2b5543eb73e12b","entry":"AtariNoveltyNet","repo":"DuaneNielsen/rnd","repo_kind":"listed","path":"novelty_policy.py","file_url":"https://github.com/DuaneNielsen/rnd/blob/HEAD/novelty_policy.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ab2b5543eb73e12b"}},{"code_sha256_prefix":"cb9601f5aff84351","entry":"CnnEncoder","repo":"balloch/rl-exploration-transfer","repo_kind":"listed","path":"rlexplore/rnd/rnd.py","file_url":"https://github.com/balloch/rl-exploration-transfer/blob/HEAD/rlexplore/rnd/rnd.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"cb9601f5aff84351"}},{"code_sha256_prefix":"2c93ef20cabcc117","entry":"MlpEncoder","repo":"balloch/rl-exploration-transfer","repo_kind":"listed","path":"rlexplore/rnd/rnd.py","file_url":"https://github.com/balloch/rl-exploration-transfer/blob/HEAD/rlexplore/rnd/rnd.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2c93ef20cabcc117"}},{"code_sha256_prefix":"1041ee8730b41597","entry":"Model","repo":"michalnand/reinforcement_learning","repo_kind":"listed","path":"experiments/atari_easy/breakout/models/ppo_rnd/src/model_rnd.py","file_url":"https://github.com/michalnand/reinforcement_learning/blob/HEAD/experiments/atari_easy/breakout/models/ppo_rnd/src/model_rnd.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1041ee8730b41597"}},{"code_sha256_prefix":"12f3d1927fc20cf0","entry":"ModelConfig","repo":"jhare96/reinforcement-learning","repo_kind":"listed","path":"rlib/RND/model.py","file_url":"https://github.com/jhare96/reinforcement-learning/blob/HEAD/rlib/RND/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"12f3d1927fc20cf0"}},{"code_sha256_prefix":"7e1ba7514a47399e","entry":"Motivator","repo":"riveSunder/carle","repo_kind":"listed","path":"carle/mcl.py","file_url":"https://github.com/riveSunder/carle/blob/HEAD/carle/mcl.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7e1ba7514a47399e"}},{"code_sha256_prefix":"4b17ba7e1f439380","entry":"NoveltyPolicy","repo":"DuaneNielsen/rnd","repo_kind":"listed","path":"novelty_policy.py","file_url":"https://github.com/DuaneNielsen/rnd/blob/HEAD/novelty_policy.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"4b17ba7e1f439380"}},{"code_sha256_prefix":"a247afb083cad9ff","entry":"PPOConfig","repo":"jhare96/reinforcement-learning","repo_kind":"listed","path":"rlib/RND/model.py","file_url":"https://github.com/jhare96/reinforcement-learning/blob/HEAD/rlib/RND/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a247afb083cad9ff"}},{"code_sha256_prefix":"ca383711596ca4f8","entry":"PredictorModel","repo":"alirezakazemipour/ppo-rnd","repo_kind":"listed","path":"Brain/model.py","file_url":"https://github.com/alirezakazemipour/ppo-rnd/blob/HEAD/Brain/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ca383711596ca4f8"}},{"code_sha256_prefix":"e654e54d98b9fc45","entry":"RND","repo":"forevergj/multithreading_ppo_RND","repo_kind":"listed","path":"brain_md.py","file_url":"https://github.com/forevergj/multithreading_ppo_RND/blob/HEAD/brain_md.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e654e54d98b9fc45"}},{"code_sha256_prefix":"7aa70f2869c53e71","entry":"RND","repo":"balloch/rl-exploration-transfer","repo_kind":"listed","path":"rlexplore/rnd/rnd.py","file_url":"https://github.com/balloch/rl-exploration-transfer/blob/HEAD/rlexplore/rnd/rnd.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7aa70f2869c53e71"}},{"code_sha256_prefix":"58bcd9d56221fa05","entry":"RND2D","repo":"riveSunder/carle","repo_kind":"listed","path":"carle/mcl.py","file_url":"https://github.com/riveSunder/carle/blob/HEAD/carle/mcl.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"58bcd9d56221fa05"}},{"code_sha256_prefix":"8f69014b9b699054","entry":"RNDModel","repo":"jcwleo/random-network-distillation-pytorch","repo_kind":"listed","path":"model.py","file_url":"https://github.com/jcwleo/random-network-distillation-pytorch/blob/HEAD/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8f69014b9b699054"}},{"code_sha256_prefix":"be1c87bf6f5e3486","entry":"RNDNetwork","repo":"uoe-agents/derl","repo_kind":"listed","path":"derl/intrinsic_rewards/rnd/rnd.py","file_url":"https://github.com/uoe-agents/derl/blob/HEAD/derl/intrinsic_rewards/rnd/rnd.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"be1c87bf6f5e3486"}},{"code_sha256_prefix":"dcfcd26f3e5c57ad","entry":"TargetModel","repo":"Justkim/random-network-distillation-pytorch","repo_kind":"listed","path":"rnd_model.py","file_url":"https://github.com/Justkim/random-network-distillation-pytorch/blob/HEAD/rnd_model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"dcfcd26f3e5c57ad"}},{"code_sha256_prefix":"147627e47de141ae","entry":"build_sequential","repo":"uoe-agents/derl","repo_kind":"listed","path":"derl/intrinsic_rewards/rnd/rnd.py","file_url":"https://github.com/uoe-agents/derl/blob/HEAD/derl/intrinsic_rewards/rnd/rnd.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"147627e47de141ae"}},{"code_sha256_prefix":"3212247a9c7830c7","entry":"conv_output_shape","repo":"DuaneNielsen/rnd","repo_kind":"listed","path":"novelty_policy.py","file_url":"https://github.com/DuaneNielsen/rnd/blob/HEAD/novelty_policy.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"3212247a9c7830c7"}},{"code_sha256_prefix":"7c4ff1e9e5bf27f4","entry":"conv_shape","repo":"alirezakazemipour/ppo-rnd","repo_kind":"listed","path":"Brain/model.py","file_url":"https://github.com/alirezakazemipour/ppo-rnd/blob/HEAD/Brain/model.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7c4ff1e9e5bf27f4"}},{"code_sha256_prefix":"df69c0a5d85d8bc3","entry":"flatten","repo":"uoe-agents/derl","repo_kind":"listed","path":"derl/intrinsic_rewards/rnd/rnd.py","file_url":"https://github.com/uoe-agents/derl/blob/HEAD/derl/intrinsic_rewards/rnd/rnd.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"df69c0a5d85d8bc3"}},{"code_sha256_prefix":"4bd07d2275540030","entry":"model","repo":"jakegrigsby/supersonic","repo_kind":"listed","path":"supersonic/models.py","file_url":"https://github.com/jakegrigsby/supersonic/blob/HEAD/supersonic/models.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"4bd07d2275540030"}},{"code_sha256_prefix":"7c704f729de99c78","entry":"orthogonal_initializer","repo":"Francesco-Sovrano/Combining--experience-replay--with--exploration-by-random-network-distillation-","repo_kind":"listed","path":"framework/agent/network/intrinsic_reward/intrinsic_reward_network.py","file_url":"https://github.com/Francesco-Sovrano/Combining--experience-replay--with--exploration-by-random-network-distillation-/blob/HEAD/framework/agent/network/intrinsic_reward/intrinsic_reward_network.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7c704f729de99c78"}},{"code_sha256_prefix":"a99332a9cc3b7293","entry":"polynomial_sheduler","repo":"jhare96/reinforcement-learning","repo_kind":"listed","path":"rlib/RND/model.py","file_url":"https://github.com/jhare96/reinforcement-learning/blob/HEAD/rlib/RND/model.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a99332a9cc3b7293"}},{"code_sha256_prefix":"2fe739431c704a67","entry":"prod","repo":"uoe-agents/derl","repo_kind":"listed","path":"derl/intrinsic_rewards/rnd/rnd.py","file_url":"https://github.com/uoe-agents/derl/blob/HEAD/derl/intrinsic_rewards/rnd/rnd.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2fe739431c704a67"}},{"code_sha256_prefix":"ca8d4b1715a4e662","entry":"tonumpy","repo":"jhare96/reinforcement-learning","repo_kind":"listed","path":"rlib/RND/model.py","file_url":"https://github.com/jhare96/reinforcement-learning/blob/HEAD/rlib/RND/model.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ca8d4b1715a4e662"}},{"code_sha256_prefix":"3ab1bc57b4217bc7","entry":"totorch","repo":"jhare96/reinforcement-learning","repo_kind":"listed","path":"rlib/RND/model.py","file_url":"https://github.com/jhare96/reinforcement-learning/blob/HEAD/rlib/RND/model.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"3ab1bc57b4217bc7"}},{"code_sha256_prefix":"d1f045c24bd9b2b9","entry":"Agent","repo":"jhare96/reinforcement-learning","repo_kind":"listed","path":"rlib/RND/model.py","file_url":"https://github.com/jhare96/reinforcement-learning/blob/HEAD/rlib/RND/model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d1f045c24bd9b2b9"}},{"code_sha256_prefix":"edb8cf6be635e983","entry":"ExplorationTarget","repo":"jakegrigsby/supersonic","repo_kind":"listed","path":"supersonic/models.py","file_url":"https://github.com/jakegrigsby/supersonic/blob/HEAD/supersonic/models.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"edb8cf6be635e983"}},{"code_sha256_prefix":"a04129b701562203","entry":"IntrinsicReward","repo":"uoe-agents/derl","repo_kind":"listed","path":"derl/intrinsic_rewards/rnd/rnd.py","file_url":"https://github.com/uoe-agents/derl/blob/HEAD/derl/intrinsic_rewards/rnd/rnd.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a04129b701562203"}},{"code_sha256_prefix":"ebbe3600bbc2b502","entry":"IntrinsicReward_Network","repo":"Francesco-Sovrano/Combining--experience-replay--with--exploration-by-random-network-distillation-","repo_kind":"listed","path":"framework/agent/network/intrinsic_reward/intrinsic_reward_network.py","file_url":"https://github.com/Francesco-Sovrano/Combining--experience-replay--with--exploration-by-random-network-distillation-/blob/HEAD/framework/agent/network/intrinsic_reward/intrinsic_reward_network.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ebbe3600bbc2b502"}},{"code_sha256_prefix":"f7540dc011b71e5d","entry":"Network","repo":"Francesco-Sovrano/Combining--experience-replay--with--exploration-by-random-network-distillation-","repo_kind":"listed","path":"framework/agent/network/intrinsic_reward/intrinsic_reward_network.py","file_url":"https://github.com/Francesco-Sovrano/Combining--experience-replay--with--exploration-by-random-network-distillation-/blob/HEAD/framework/agent/network/intrinsic_reward/intrinsic_reward_network.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f7540dc011b71e5d"}},{"code_sha256_prefix":"4fd2cec5b421371d","entry":"PPOIntrinsic","repo":"jhare96/reinforcement-learning","repo_kind":"listed","path":"rlib/RND/model.py","file_url":"https://github.com/jhare96/reinforcement-learning/blob/HEAD/rlib/RND/model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"4fd2cec5b421371d"}},{"code_sha256_prefix":"b748fd36e9fb6640","entry":"PPOModel","repo":"jhare96/reinforcement-learning","repo_kind":"listed","path":"rlib/RND/model.py","file_url":"https://github.com/jhare96/reinforcement-learning/blob/HEAD/rlib/RND/model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b748fd36e9fb6640"}},{"code_sha256_prefix":"920f08f608d008cb","entry":"Policy","repo":"DuaneNielsen/rnd","repo_kind":"listed","path":"novelty_policy.py","file_url":"https://github.com/DuaneNielsen/rnd/blob/HEAD/novelty_policy.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"920f08f608d008cb"}},{"code_sha256_prefix":"ed8d297030cd46b1","entry":"RND","repo":"jhare96/reinforcement-learning","repo_kind":"listed","path":"rlib/RND/model.py","file_url":"https://github.com/jhare96/reinforcement-learning/blob/HEAD/rlib/RND/model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ed8d297030cd46b1"}},{"code_sha256_prefix":"96d5517e9763275d","entry":"RND","repo":"uoe-agents/derl","repo_kind":"listed","path":"derl/intrinsic_rewards/rnd/rnd.py","file_url":"https://github.com/uoe-agents/derl/blob/HEAD/derl/intrinsic_rewards/rnd/rnd.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"96d5517e9763275d"}},{"code_sha256_prefix":"0ca7ce32a4f2492c","entry":"discount","repo":"microsoft/strategically_efficient_rl","repo_kind":"listed","path":"algorithms/agents/intrinsic.py","file_url":"https://github.com/microsoft/strategically_efficient_rl/blob/HEAD/algorithms/agents/intrinsic.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0ca7ce32a4f2492c"}},{"code_sha256_prefix":"b1c9a4762c24dd86","entry":"get_best_configs","repo":"microsoft/strategically_efficient_rl","repo_kind":"listed","path":"analyze_hyperparameters.py","file_url":"https://github.com/microsoft/strategically_efficient_rl/blob/HEAD/analyze_hyperparameters.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b1c9a4762c24dd86"}},{"code_sha256_prefix":"85c397ba249397f2","entry":"load_experiments","repo":"microsoft/strategically_efficient_rl","repo_kind":"listed","path":"plot_runs_csv.py","file_url":"https://github.com/microsoft/strategically_efficient_rl/blob/HEAD/plot_runs_csv.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"85c397ba249397f2"}},{"code_sha256_prefix":"779387c1139ff5c3","entry":"load_last_checkpoint","repo":"microsoft/strategically_efficient_rl","repo_kind":"listed","path":"visualize_gym_atari.py","file_url":"https://github.com/microsoft/strategically_efficient_rl/blob/HEAD/visualize_gym_atari.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"779387c1139ff5c3"}},{"code_sha256_prefix":"4123e2d8163b9224","entry":"nash_conv","repo":"microsoft/strategically_efficient_rl","repo_kind":"listed","path":"train_multiagent.py","file_url":"https://github.com/microsoft/strategically_efficient_rl/blob/HEAD/train_multiagent.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4123e2d8163b9224"}},{"code_sha256_prefix":"8a7ed7f9726866e9","entry":"rogue_config","repo":"kngwyu/intrinsic-rewards","repo_kind":"listed","path":"experiments/ppo_roguegym.py","file_url":"https://github.com/kngwyu/intrinsic-rewards/blob/HEAD/experiments/ppo_roguegym.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"8a7ed7f9726866e9"}},{"code_sha256_prefix":"82f14c9f59ca7edc","entry":"totorch_many","repo":"jhare96/reinforcement-learning","repo_kind":"listed","path":"rlib/RND/model.py","file_url":"https://github.com/jhare96/reinforcement-learning/blob/HEAD/rlib/RND/model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"82f14c9f59ca7edc"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}