{"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-agent","entry":"make_agent","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":20,"n_papers_ran":4,"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":11,"n_samples_ran":4,"n_samples_fingerprinted":0,"n_places":24,"n_places_pointer_only":9,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":3,"ran_fixture":0,"ran":1,"unverified":7},"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":"2506.05980","paper":"/paper/amped-adaptive-multi-objective-projection-for","title":"AMPED: Adaptive Multi-objective Projection for balancing Exploration and skill Diversification","date":"2025-06-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":null,"inline_ok":false,"code_sha256_prefix":"2a76dfe317adeb03","mcp_get_code":{"code_sha256":"2a76dfe317adeb03"}},{"arxiv_id":"2410.22133","paper":"/paper/learning-successor-features-the-simple-way","title":"Learning Successor Features the Simple Way","date":"2024-10-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"raymondchua/simple_successor_features","path":"full_train.py","file_url":"https://github.com/raymondchua/simple_successor_features/blob/HEAD/full_train.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"14e8a7cb98687b21","mcp_get_code":{"code_sha256":"14e8a7cb98687b21"}},{"arxiv_id":"2410.13855","paper":"/paper/diffusing-states-and-matching-scores-a-new","title":"Diffusing States and Matching Scores: A New Framework for Imitation Learning","date":"2024-10-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ziqian2000/SMILING","path":"utils.py","file_url":"https://github.com/ziqian2000/SMILING/blob/HEAD/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"524f939a65aaa2da","mcp_get_code":{"code_sha256":"524f939a65aaa2da"}},{"arxiv_id":"2406.18043","paper":"/paper/multimodal-foundation-world-models-for","title":"GenRL: Multimodal-foundation world models for generalization in embodied agents","date":"2024-06-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mazpie/genrl","path":"collect_data.py","file_url":"https://github.com/mazpie/genrl/blob/HEAD/collect_data.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2a76dfe317adeb03","mcp_get_code":{"code_sha256":"2a76dfe317adeb03"}},{"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":"offline.py","file_url":"https://github.com/uclaml/GFA-RFE/blob/HEAD/offline.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2a76dfe317adeb03","mcp_get_code":{"code_sha256":"2a76dfe317adeb03"}},{"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":"finetune.py","file_url":"https://github.com/Baichenjia/CeSD/blob/HEAD/finetune.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2a76dfe317adeb03","mcp_get_code":{"code_sha256":"2a76dfe317adeb03"}},{"arxiv_id":"2405.15223","paper":"/paper/ivideogpt-interactive-videogpts-are-scalable","title":"iVideoGPT: Interactive VideoGPTs are Scalable World Models","date":"2024-05-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":null,"inline_ok":false,"code_sha256_prefix":"f1ba293af9a573fd","mcp_get_code":{"code_sha256":"f1ba293af9a573fd"}},{"arxiv_id":"2405.14073","paper":"/paper/peac-unsupervised-pre-training-for-cross","title":"PEAC: Unsupervised Pre-training for Cross-Embodiment Reinforcement Learning","date":"2024-05-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"thu-ml/CEURL","path":"DMC_image/dreamer_finetune.py","file_url":"https://github.com/thu-ml/CEURL/blob/HEAD/DMC_image/dreamer_finetune.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2a76dfe317adeb03","mcp_get_code":{"code_sha256":"2a76dfe317adeb03"}},{"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":"train_prise.py","file_url":"https://github.com/FrankZheng2022/PRISE/blob/HEAD/train_prise.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"881c9af39ce5d3c4","mcp_get_code":{"code_sha256":"881c9af39ce5d3c4"}},{"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":"train_bc.py","file_url":"https://github.com/PremierTACO/premier-taco/blob/HEAD/train_bc.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f1ba293af9a573fd","mcp_get_code":{"code_sha256":"f1ba293af9a573fd"}},{"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":"train_premier_taco_dist.py","file_url":"https://github.com/premiertaco/premier-taco/blob/HEAD/train_premier_taco_dist.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"ff56a87a6c0c857f","mcp_get_code":{"code_sha256":"ff56a87a6c0c857f"}},{"arxiv_id":"2312.17116","paper":"/paper/generalizable-visual-reinforcement-learning","title":"Generalizable Visual Reinforcement Learning with Segment Anything Model","date":"2023-12-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"wadiuvatzy/sam-g","path":"carlatrain.py","file_url":"https://github.com/wadiuvatzy/sam-g/blob/HEAD/carlatrain.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f1ba293af9a573fd","mcp_get_code":{"code_sha256":"f1ba293af9a573fd"}},{"arxiv_id":"2307.10224","paper":"/paper/rl-vigen-a-reinforcement-learning-benchmark-1","title":"RL-ViGen: A Reinforcement Learning Benchmark for Visual Generalization","date":"2023-07-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"gemcollector/rl-vigen","path":"carlatrain.py","file_url":"https://github.com/gemcollector/rl-vigen/blob/HEAD/carlatrain.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f1ba293af9a573fd","mcp_get_code":{"code_sha256":"f1ba293af9a573fd"}},{"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":"finetune.py","file_url":"https://github.com/Rooshy-yang/BeCL/blob/HEAD/finetune.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2a76dfe317adeb03","mcp_get_code":{"code_sha256":"2a76dfe317adeb03"}},{"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/eval_robot.py","file_url":"https://github.com/siddhanthaldar/FISH/blob/HEAD/FISH/eval_robot.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"6dcf7786ccfa6051","mcp_get_code":{"code_sha256":"6dcf7786ccfa6051"}},{"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/train_hand.py","file_url":"https://github.com/siddhanthaldar/FISH/blob/HEAD/FISH/train_hand.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b6a479ef98b42e5f","mcp_get_code":{"code_sha256":"b6a479ef98b42e5f"}},{"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/train_robot.py","file_url":"https://github.com/siddhanthaldar/FISH/blob/HEAD/FISH/train_robot.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"552d3925ad4f9b07","mcp_get_code":{"code_sha256":"552d3925ad4f9b07"}},{"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/generate.py","file_url":"https://github.com/sail-sg/PatchAIL/blob/HEAD/PatchAIL/generate.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":"08c2a94185babfce","mcp_get_code":{"code_sha256":"08c2a94185babfce"}},{"arxiv_id":"2211.13350","paper":"/paper/choreographer-learning-and-adapting-skills-in","title":"Choreographer: Learning and Adapting Skills in Imagination","date":"2022-11-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mazpie/choreographer","path":"finetune.py","file_url":"https://github.com/mazpie/choreographer/blob/HEAD/finetune.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ec382ec28dcb1ad9","mcp_get_code":{"code_sha256":"ec382ec28dcb1ad9"}},{"arxiv_id":"2211.13350","paper":"/paper/choreographer-learning-and-adapting-skills-in","title":"Choreographer: Learning and Adapting Skills in Imagination","date":"2022-11-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":null,"inline_ok":false,"code_sha256_prefix":"2a76dfe317adeb03","mcp_get_code":{"code_sha256":"2a76dfe317adeb03"}},{"arxiv_id":"2202.10324","paper":"/paper/vrl3-a-data-driven-framework-for-visual-deep","title":"VRL3: A Data-Driven Framework for Visual Deep Reinforcement Learning","date":"2022-02-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"microsoft/VRL3","path":"src/train_adroit.py","file_url":"https://github.com/microsoft/VRL3/blob/HEAD/src/train_adroit.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f1ba293af9a573fd","mcp_get_code":{"code_sha256":"f1ba293af9a573fd"}},{"arxiv_id":"2202.00161","paper":"/paper/cic-contrastive-intrinsic-control-for-1","title":"CIC: Contrastive Intrinsic Control for Unsupervised Skill Discovery","date":"2022-02-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":null,"inline_ok":false,"code_sha256_prefix":"2a76dfe317adeb03","mcp_get_code":{"code_sha256":"2a76dfe317adeb03"}},{"arxiv_id":"2110.15191","paper":"/paper/urlb-unsupervised-reinforcement-learning","title":"URLB: Unsupervised Reinforcement Learning Benchmark","date":"2021-10-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":null,"inline_ok":false,"code_sha256_prefix":"2a76dfe317adeb03","mcp_get_code":{"code_sha256":"2a76dfe317adeb03"}},{"arxiv_id":"2103.04551","paper":"/paper/behavior-from-the-void-unsupervised-active","title":"Behavior From the Void: Unsupervised Active Pre-Training","date":"2021-03-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rll-research/url_benchmark","path":"pretrain.py","file_url":"https://github.com/rll-research/url_benchmark/blob/HEAD/pretrain.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2a76dfe317adeb03","mcp_get_code":{"code_sha256":"2a76dfe317adeb03"}}]}