{"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":"/code/make-atari","entry":"make_atari","source":"Syntology graph, per-sample; not an archive number","read_at":"2026-09-24T18:15:14+00:00","claim":"Names are grouped by exact entry-name string. Same-named routines are NOT asserted to be equivalent; 'ran' means executed on a synthesized fixture, not correctness. n_samples_ran = sum of by_status over every status except 'unverified' (ran_draft_wrong and ran_fixture are failures of Syntology's instrument, not of the code); n_papers_ran = papers with at least one such sample.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"n_papers":17,"n_papers_ran":5,"units":"n_samples, n_samples_ran, n_samples_fingerprinted and by_status count distinct code bodies (code_sha256); n_places and n_places_pointer_only count places, one per (paper, code body) pair, which is also the unit of the samples list","n_samples":14,"n_samples_ran":4,"n_samples_fingerprinted":0,"n_places":17,"n_places_pointer_only":5,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":4,"unverified":10},"syntology":{"atlas_url":null,"mcp":null,"mcp_per_sample":{"tool":"get_code","arguments_in":"samples[].mcp_get_code"},"developers":"https://syntology.ai/developers"},"samples":[{"arxiv_id":"2406.19320","paper":"/paper/efficient-world-models-with-context-aware","title":"Efficient World Models with Context-Aware Tokenization","date":"2024-06-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"vmicheli/delta-iris","path":"src/envs/wrappers.py","file_url":"https://github.com/vmicheli/delta-iris/blob/HEAD/src/envs/wrappers.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"code_sha256_prefix":"4ba4e8deb90aa134","mcp_get_code":{"code_sha256":"4ba4e8deb90aa134"}},{"arxiv_id":"2404.10728","paper":"/paper/randomized-exploration-in-cooperative-multi","title":"Randomized Exploration in Cooperative Multi-Agent Reinforcement Learning","date":"2024-04-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"panxulab/MARL-CoopTS","path":"Envs/wrapper.py","file_url":"https://github.com/panxulab/MARL-CoopTS/blob/HEAD/Envs/wrapper.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"97d520547d641ca3","mcp_get_code":{"code_sha256":"97d520547d641ca3"}},{"arxiv_id":"2404.05440","paper":"/paper/tree-search-based-policy-optimization-under","title":"Tree Search-Based Policy Optimization under Stochastic Execution Delay","date":"2024-04-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"davidva1/Delayed-EZ","path":"core/utils.py","file_url":"https://github.com/davidva1/Delayed-EZ/blob/HEAD/core/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"code_sha256_prefix":"461cd9ba90efb8ac","mcp_get_code":{"code_sha256":"461cd9ba90efb8ac"}},{"arxiv_id":"2402.09844","paper":"/paper/jack-of-all-trades-master-of-some-a-multi","title":"Jack of All Trades, Master of Some, a Multi-Purpose Transformer Agent","date":"2024-02-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"huggingface/jat","path":"jat/eval/rl/core.py","file_url":"https://github.com/huggingface/jat/blob/HEAD/jat/eval/rl/core.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"ff3946a18bfa4ec9","mcp_get_code":{"code_sha256":"ff3946a18bfa4ec9"}},{"arxiv_id":"2402.02165","paper":"/paper/towards-optimal-adversarial-robust-q-learning","title":"Towards Optimal Adversarial Robust Q-learning with Bellman Infinity-error","date":"2024-02-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"leoranlmia/CAR-DQN","path":"IBP/environment.py","file_url":"https://github.com/leoranlmia/CAR-DQN/blob/HEAD/IBP/environment.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"c8ff0fd6f22e92e8","mcp_get_code":{"code_sha256":"c8ff0fd6f22e92e8"}},{"arxiv_id":"2210.10763","paper":"/paper/on-the-feasibility-of-cross-task-transfer","title":"On the Feasibility of Cross-Task Transfer with Model-Based Reinforcement Learning","date":"2022-10-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mlpc-ucsd/xtra","path":"src/core/utils.py","file_url":"https://github.com/mlpc-ucsd/xtra/blob/HEAD/src/core/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"11b2c75d0350f659","mcp_get_code":{"code_sha256":"11b2c75d0350f659"}},{"arxiv_id":"2201.07211","paper":"/paper/human-level-control-through-directly-trained","title":"Human-Level Control through Directly-Trained Deep Spiking Q-Networks","date":"2021-12-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"aptx395/deep-spiking-q-networks","path":"environment/atari_wrappers.py","file_url":"https://github.com/aptx395/deep-spiking-q-networks/blob/HEAD/environment/atari_wrappers.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a70a2154eb543432","mcp_get_code":{"code_sha256":"a70a2154eb543432"}},{"arxiv_id":"2111.03941","paper":"/paper/time-discretization-invariant-safe-action","title":"Time Discretization-Invariant Safe Action Repetition for Policy Gradient Methods","date":"2021-11-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"artberryx/SAR","path":"sb/stable_baselines/common/atari_wrappers.py","file_url":"https://github.com/artberryx/SAR/blob/HEAD/sb/stable_baselines/common/atari_wrappers.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"42dca35d1e009c9a","mcp_get_code":{"code_sha256":"42dca35d1e009c9a"}},{"arxiv_id":"2006.04061","paper":"/paper/dual-policy-distillation","title":"Dual Policy Distillation","date":"2020-06-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kiminh/dual-policy-distillation","path":"baselines/common/atari_wrappers.py","file_url":"https://github.com/kiminh/dual-policy-distillation/blob/HEAD/baselines/common/atari_wrappers.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"code_sha256_prefix":"186018cc4315055f","mcp_get_code":{"code_sha256":"186018cc4315055f"}},{"arxiv_id":"2002.04839","paper":"/paper/laprop-a-better-way-to-combine-momentum-with","title":"LaProp: Separating Momentum and Adaptivity in Adam","date":"2020-02-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Z-T-WANG/LaProp-Optimizer","path":"rainbow/common/wrappers.py","file_url":"https://github.com/Z-T-WANG/LaProp-Optimizer/blob/HEAD/rainbow/common/wrappers.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"6eb2fa89d6e4a36b","mcp_get_code":{"code_sha256":"6eb2fa89d6e4a36b"}},{"arxiv_id":"1911.02140","paper":"/paper/fully-parameterized-quantile-function-for","title":"Fully Parameterized Quantile Function for Distributional Reinforcement Learning","date":"2019-11-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ku2482/fqf-iqn-qrdqn.pytorch","path":"fqf_iqn_qrdqn/env.py","file_url":"https://github.com/ku2482/fqf-iqn-qrdqn.pytorch/blob/HEAD/fqf_iqn_qrdqn/env.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4bc698f17fe89d85","mcp_get_code":{"code_sha256":"4bc698f17fe89d85"}},{"arxiv_id":"1910.12154","paper":"/paper/zpd-teaching-strategies-for-deep","title":"ZPD Teaching Strategies for Deep Reinforcement Learning from Demonstrations","date":"2019-10-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"RevanMacQueen/LearningFromHumans","path":"lfh/envs/atari.py","file_url":"https://github.com/RevanMacQueen/LearningFromHumans/blob/HEAD/lfh/envs/atari.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"cf49e0670274da2b","mcp_get_code":{"code_sha256":"cf49e0670274da2b"}},{"arxiv_id":"1910.07207","paper":"/paper/soft-actor-critic-for-discrete-action","title":"Soft Actor-Critic for Discrete Action Settings","date":"2019-10-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"cindycia/Atari-SAC-Discrete","path":"rltorch/env/atari_wrappers.py","file_url":"https://github.com/cindycia/Atari-SAC-Discrete/blob/HEAD/rltorch/env/atari_wrappers.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4bc698f17fe89d85","mcp_get_code":{"code_sha256":"4bc698f17fe89d85"}},{"arxiv_id":"1905.02363","paper":"/paper/dimension-wise-importance-sampling-weight","title":"Dimension-Wise Importance Sampling Weight Clipping for Sample-Efficient Reinforcement Learning","date":"2019-05-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"seungyulhan/disc","path":"baselines/common/atari_wrappers.py","file_url":"https://github.com/seungyulhan/disc/blob/HEAD/baselines/common/atari_wrappers.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"code_sha256_prefix":"b013c9fa08f46d68","mcp_get_code":{"code_sha256":"b013c9fa08f46d68"}},{"arxiv_id":"1703.01988","paper":"/paper/neural-episodic-control","title":"Neural Episodic Control","date":"2017-03-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mjacar/pytorch-nec","path":"utils/atari_wrapper.py","file_url":"https://github.com/mjacar/pytorch-nec/blob/HEAD/utils/atari_wrapper.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"309ae4ee61c2c6a1","mcp_get_code":{"code_sha256":"309ae4ee61c2c6a1"}},{"arxiv_id":"1511.06581","paper":"/paper/dueling-network-architectures-for-deep","title":"Dueling Network Architectures for Deep Reinforcement Learning","date":"2015-11-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"opplieam/Pong-Deep-RL","path":"atari_wrappers.py","file_url":"https://github.com/opplieam/Pong-Deep-RL/blob/HEAD/atari_wrappers.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"c8ff0fd6f22e92e8","mcp_get_code":{"code_sha256":"c8ff0fd6f22e92e8"}},{"arxiv_id":"1509.06461","paper":"/paper/deep-reinforcement-learning-with-double-q","title":"Deep Reinforcement Learning with Double Q-learning","date":"2015-09-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jihoonerd/Deep-Reinforcement-Learning-with-Double-Q-learning","path":"ddqn/utils/atari_wrappers.py","file_url":"https://github.com/jihoonerd/Deep-Reinforcement-Learning-with-Double-Q-learning/blob/HEAD/ddqn/utils/atari_wrappers.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a70a2154eb543432","mcp_get_code":{"code_sha256":"a70a2154eb543432"}}]}