{"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/episode-len","entry":"episode_len","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":14,"n_papers_ran":13,"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":2,"n_samples_ran":1,"n_samples_fingerprinted":0,"n_places":14,"n_places_pointer_only":2,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":1,"unverified":1},"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":"2608.07870","paper":"/paper/arxiv-2608-07870","title":"V-Simba: Unleashing the Architectural Potential of RL in Visual Continuous Control","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"FrankZheng2022/TACO","path":"replay_buffer.py","file_url":"https://github.com/FrankZheng2022/TACO/blob/HEAD/replay_buffer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9f840a22d31a89bc","mcp_get_code":{"code_sha256":"9f840a22d31a89bc"}},{"arxiv_id":"2505.24710","paper":"/paper/causal-aware-large-language-models-enhancing","title":"Causal-aware Large Language Models: Enhancing Decision-Making Through Learning, Adapting and Acting","date":"2025-05-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dmirlab-group/causal-aware_llms","path":"replay_buffer.py","file_url":"https://github.com/dmirlab-group/causal-aware_llms/blob/HEAD/replay_buffer.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"6dc883bc1585e237","mcp_get_code":{"code_sha256":"6dc883bc1585e237"}},{"arxiv_id":"2410.21795","paper":"/paper/robot-policy-learning-with-temporal-optimal","title":"Robot Policy Learning with Temporal Optimal Transport Reward","date":"2024-10-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"fuyw/TemporalOT","path":"utils/buffer_utils.py","file_url":"https://github.com/fuyw/TemporalOT/blob/HEAD/utils/buffer_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"9f840a22d31a89bc","mcp_get_code":{"code_sha256":"9f840a22d31a89bc"}},{"arxiv_id":"2406.16255","paper":"/paper/uncertainty-aware-reward-free-exploration","title":"Uncertainty-Aware Reward-Free Exploration with General Function Approximation","date":"2024-06-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"uclaml/GFA-RFE","path":"replay_buffer.py","file_url":"https://github.com/uclaml/GFA-RFE/blob/HEAD/replay_buffer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9f840a22d31a89bc","mcp_get_code":{"code_sha256":"9f840a22d31a89bc"}},{"arxiv_id":"2405.17416","paper":"/paper/a-recipe-for-unbounded-data-augmentation-in","title":"A Recipe for Unbounded Data Augmentation in Visual Reinforcement Learning","date":"2024-05-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"aalmuzairee/dmcgb2","path":"replay_buffer.py","file_url":"https://github.com/aalmuzairee/dmcgb2/blob/HEAD/replay_buffer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9f840a22d31a89bc","mcp_get_code":{"code_sha256":"9f840a22d31a89bc"}},{"arxiv_id":"2405.16907","paper":"/paper/gta-generative-trajectory-augmentation-with","title":"GTA: Generative Trajectory Augmentation with Guidance for Offline Reinforcement Learning","date":"2024-05-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"conglu1997/v-d4rl","path":"drqbc/replay_buffer.py","file_url":"https://github.com/conglu1997/v-d4rl/blob/HEAD/drqbc/replay_buffer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9f840a22d31a89bc","mcp_get_code":{"code_sha256":"9f840a22d31a89bc"}},{"arxiv_id":"2405.16030","paper":"/paper/constrained-ensemble-exploration-for","title":"Constrained Ensemble Exploration for Unsupervised Skill Discovery","date":"2024-05-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Baichenjia/CeSD","path":"replay_buffer.py","file_url":"https://github.com/Baichenjia/CeSD/blob/HEAD/replay_buffer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9f840a22d31a89bc","mcp_get_code":{"code_sha256":"9f840a22d31a89bc"}},{"arxiv_id":"2402.10450","paper":"/paper/prise-learning-temporal-action-abstractions","title":"PRISE: LLM-Style Sequence Compression for Learning Temporal Action Abstractions in Control","date":"2024-02-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"frankzheng2022/prise","path":"replay_buffer.py","file_url":"https://github.com/frankzheng2022/prise/blob/HEAD/replay_buffer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9f840a22d31a89bc","mcp_get_code":{"code_sha256":"9f840a22d31a89bc"}},{"arxiv_id":"2402.06187","paper":"/paper/premier-taco-pretraining-multitask","title":"Premier-TACO is a Few-Shot Policy Learner: Pretraining Multitask Representation via Temporal Action-Driven Contrastive Loss","date":"2024-02-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"PremierTACO/premier-taco","path":"replay_buffer.py","file_url":"https://github.com/PremierTACO/premier-taco/blob/HEAD/replay_buffer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"9f840a22d31a89bc","mcp_get_code":{"code_sha256":"9f840a22d31a89bc"}},{"arxiv_id":"2305.04477","paper":"/paper/behavior-contrastive-learning-for","title":"Behavior Contrastive Learning for Unsupervised Skill Discovery","date":"2023-05-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Rooshy-yang/BeCL","path":"replay_buffer.py","file_url":"https://github.com/Rooshy-yang/BeCL/blob/HEAD/replay_buffer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9f840a22d31a89bc","mcp_get_code":{"code_sha256":"9f840a22d31a89bc"}},{"arxiv_id":"2303.01497","paper":"/paper/teach-a-robot-to-fish-versatile-imitation","title":"Teach a Robot to FISH: Versatile Imitation from One Minute of Demonstrations","date":"2023-03-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"siddhanthaldar/FISH","path":"FISH/replay_buffer_hand.py","file_url":"https://github.com/siddhanthaldar/FISH/blob/HEAD/FISH/replay_buffer_hand.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9f840a22d31a89bc","mcp_get_code":{"code_sha256":"9f840a22d31a89bc"}},{"arxiv_id":"2302.00965","paper":"/paper/visual-imitation-learning-with-patch-rewards","title":"Visual Imitation Learning with Patch Rewards","date":"2023-02-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sail-sg/PatchAIL","path":"PatchAIL/replay_buffer.py","file_url":"https://github.com/sail-sg/PatchAIL/blob/HEAD/PatchAIL/replay_buffer.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":"9f840a22d31a89bc","mcp_get_code":{"code_sha256":"9f840a22d31a89bc"}},{"arxiv_id":"2211.12740","paper":"/paper/masked-autoencoding-for-scalable-and","title":"Masked Autoencoding for Scalable and Generalizable Decision Making","date":"2022-11-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"fangchenliu/maskdp_public","path":"replay_buffer.py","file_url":"https://github.com/fangchenliu/maskdp_public/blob/HEAD/replay_buffer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9f840a22d31a89bc","mcp_get_code":{"code_sha256":"9f840a22d31a89bc"}},{"arxiv_id":"2107.09645","paper":"/paper/mastering-visual-continuous-control-improved","title":"Mastering Visual Continuous Control: Improved Data-Augmented Reinforcement Learning","date":"2021-07-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zhou-henry/distributed-distributional-drq","path":"replay_buffer.py","file_url":"https://github.com/zhou-henry/distributed-distributional-drq/blob/HEAD/replay_buffer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9f840a22d31a89bc","mcp_get_code":{"code_sha256":"9f840a22d31a89bc"}}]}