{"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/leveraging-procedural-generation-to-benchmark","title":"Leveraging Procedural Generation to Benchmark Reinforcement Learning","arxiv_id":"1912.01588","date":"2019-12-03","proceeding":"ICML 2020 1","authors":["Karl Cobbe","Christopher Hesse","Jacob Hilton","John Schulman"],"abstract":"We introduce Procgen Benchmark, a suite of 16 procedurally generated game-like environments designed to benchmark both sample efficiency and generalization in reinforcement learning. We believe that the community will benefit from increased access to high quality training environments, and we provide detailed experimental protocols for using this benchmark. We empirically demonstrate that diverse environment distributions are essential to adequately train and evaluate RL agents, thereby motivating the extensive use of procedural content generation. We then use this benchmark to investigate the effects of scaling model size, finding that larger models significantly improve both sample efficiency and generalization.","url_abs":"https://arxiv.org/abs/1912.01588v2","url_pdf":"https://arxiv.org/pdf/1912.01588v2.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":"leveraging-procedural-generation-to-benchmark","repo_url":"https://github.com/openai/procgen","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"leveraging-procedural-generation-to-benchmark","repo_url":"https://github.com/openai/train-procgen","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"leveraging-procedural-generation-to-benchmark","repo_url":"https://github.com/ana-tudor/classyconditioning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"leveraging-procedural-generation-to-benchmark","repo_url":"https://github.com/joonleesky/train-procgen-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"leveraging-procedural-generation-to-benchmark","repo_url":"https://github.com/rgilman33/carlita","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"leveraging-procedural-generation-to-benchmark","repo_url":"https://github.com/zxtan98/cprocgen","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"procgen-hard-100m","task_name":"Procgen Hard (100M)"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[],"datasets_introduced":[{"slug":"procgen","name":"ProcGen","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1912.01588","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1912.01588"}},"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/procgen","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/joonleesky/train-procgen-pytorch","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/rgilman33/carlita","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/openai/train-procgen","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ana-tudor/classyconditioning","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/zxtan98/cprocgen","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":3,"ran_fixture":1,"ran":1,"ran_honours":2,"ran_violates":1,"unverified":7},"by_repo_kind":{"official":{"samples":3,"ran":0,"repositories":1},"listed":{"samples":12,"ran":8,"repositories":3}},"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":12,"samples":[{"code_sha256_prefix":"8758308dc6c0727f","entry":"constfn","repo":"ana-tudor/classyconditioning","repo_kind":"listed","path":"fruitbot_ppo/ppo_agent.py","file_url":"https://github.com/ana-tudor/classyconditioning/blob/HEAD/fruitbot_ppo/ppo_agent.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"8758308dc6c0727f"}},{"code_sha256_prefix":"d3319e3d34ca90ca","entry":"drop_connect","repo":"rgilman33/carlita","repo_kind":"listed","path":"efficientnet_utils.py","file_url":"https://github.com/rgilman33/carlita/blob/HEAD/efficientnet_utils.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"d3319e3d34ca90ca"}},{"code_sha256_prefix":"f15a49337e69e937","entry":"round_filters","repo":"rgilman33/carlita","repo_kind":"listed","path":"efficientnet_utils.py","file_url":"https://github.com/rgilman33/carlita/blob/HEAD/efficientnet_utils.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"f15a49337e69e937"}},{"code_sha256_prefix":"dbc0ca08d119a5a0","entry":"round_repeats","repo":"rgilman33/carlita","repo_kind":"listed","path":"efficientnet_utils.py","file_url":"https://github.com/rgilman33/carlita/blob/HEAD/efficientnet_utils.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"dbc0ca08d119a5a0"}},{"code_sha256_prefix":"1067e655bdab66ee","entry":"run","repo":"rgilman33/carlita","repo_kind":"listed","path":"procgen/build.py","file_url":"https://github.com/rgilman33/carlita/blob/HEAD/procgen/build.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"1067e655bdab66ee"}},{"code_sha256_prefix":"a7b323241cd70612","entry":"safemean","repo":"ana-tudor/classyconditioning","repo_kind":"listed","path":"fruitbot_ppo/ppo_agent.py","file_url":"https://github.com/ana-tudor/classyconditioning/blob/HEAD/fruitbot_ppo/ppo_agent.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"a7b323241cd70612"}},{"code_sha256_prefix":"baf2a28d376d7803","entry":"sf01","repo":"ana-tudor/classyconditioning","repo_kind":"listed","path":"fruitbot_ppo/epopt_runner.py","file_url":"https://github.com/ana-tudor/classyconditioning/blob/HEAD/fruitbot_ppo/epopt_runner.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"baf2a28d376d7803"}},{"code_sha256_prefix":"3ebb420a5d10cc64","entry":"update_mean_var_count_from_moments","repo":"joonleesky/train-procgen-pytorch","repo_kind":"listed","path":"common/env/procgen_wrappers.py","file_url":"https://github.com/joonleesky/train-procgen-pytorch/blob/HEAD/common/env/procgen_wrappers.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"3ebb420a5d10cc64"}},{"code_sha256_prefix":"5d6006f62f7660ef","entry":"build_reg_impala_cnn","repo":"ana-tudor/classyconditioning","repo_kind":"listed","path":"fruitbot_ppo/reg_impala_cnn.py","file_url":"https://github.com/ana-tudor/classyconditioning/blob/HEAD/fruitbot_ppo/reg_impala_cnn.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":false,"mcp_get_code":{"code_sha256":"5d6006f62f7660ef"}},{"code_sha256_prefix":"f9d33adb8b6ca4d2","entry":"build_reg_impala_cnn_verbose","repo":"ana-tudor/classyconditioning","repo_kind":"listed","path":"fruitbot_ppo/reg_impala_cnn.py","file_url":"https://github.com/ana-tudor/classyconditioning/blob/HEAD/fruitbot_ppo/reg_impala_cnn.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":false,"mcp_get_code":{"code_sha256":"f9d33adb8b6ca4d2"}},{"code_sha256_prefix":"a362c435a091c0f4","entry":"ema","repo":"openai/train-procgen","repo_kind":"official","path":"train_procgen/graph_util.py","file_url":"https://github.com/openai/train-procgen/blob/HEAD/train_procgen/graph_util.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":"a362c435a091c0f4"}},{"code_sha256_prefix":"3a87e9cb29c5eff4","entry":"get_hidden","repo":"rgilman33/carlita","repo_kind":"listed","path":"train_utils.py","file_url":"https://github.com/rgilman33/carlita/blob/HEAD/train_utils.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":false,"mcp_get_code":{"code_sha256":"3a87e9cb29c5eff4"}},{"code_sha256_prefix":"fa2053a8568916ec","entry":"get_var","repo":"rgilman33/carlita","repo_kind":"listed","path":"procgen-build/procgen_build/build_package.py","file_url":"https://github.com/rgilman33/carlita/blob/HEAD/procgen-build/procgen_build/build_package.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":false,"mcp_get_code":{"code_sha256":"fa2053a8568916ec"}},{"code_sha256_prefix":"b5e9129d63af4909","entry":"read_csv","repo":"openai/train-procgen","repo_kind":"official","path":"train_procgen/graph_util.py","file_url":"https://github.com/openai/train-procgen/blob/HEAD/train_procgen/graph_util.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":"b5e9129d63af4909"}},{"code_sha256_prefix":"a080ad6d9c26a9e9","entry":"switch_to_outer_plot","repo":"openai/train-procgen","repo_kind":"official","path":"train_procgen/graph_util.py","file_url":"https://github.com/openai/train-procgen/blob/HEAD/train_procgen/graph_util.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":"a080ad6d9c26a9e9"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}