{"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/compute-policy-gradient-loss","entry":"compute_policy_gradient_loss","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":8,"n_papers_ran":7,"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":5,"n_samples_ran":4,"n_samples_fingerprinted":1,"n_places":8,"n_places_pointer_only":6,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":4,"ran_fixture":0,"ran":0,"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":"2210.00066","paper":"/paper/improving-policy-learning-via-language","title":"Improving Policy Learning via Language Dynamics Distillation","date":"2022-09-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"facebookresearch/nle","path":"nle/agent/agent.py","file_url":"https://github.com/facebookresearch/nle/blob/HEAD/nle/agent/agent.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"f46896c3a13fa416","mcp_get_code":{"code_sha256":"f46896c3a13fa416"}},{"arxiv_id":"2201.03544","paper":"/paper/the-effects-of-reward-misspecification-1","title":"The Effects of Reward Misspecification: Mapping and Mitigating Misaligned Models","date":"2022-01-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"aypan17/reward-misspecification","path":"atari/torchbeast/monobeast.py","file_url":"https://github.com/aypan17/reward-misspecification/blob/HEAD/atari/torchbeast/monobeast.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d6d7e0906f1c57b2","mcp_get_code":{"code_sha256":"d6d7e0906f1c57b2"}},{"arxiv_id":"2111.13119","paper":"/paper/interesting-object-curious-agent-learning-1","title":"Interesting Object, Curious Agent: Learning Task-Agnostic Exploration","date":"2021-11-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"code_sha256_prefix":"6189aef0d2a9d6aa","mcp_get_code":{"code_sha256":"6189aef0d2a9d6aa"}},{"arxiv_id":"2006.12122","paper":"/paper/learning-with-amigo-adversarially-motivated","title":"Learning with AMIGo: Adversarially Motivated Intrinsic Goals","date":"2020-06-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"facebookresearch/adversarially-motivated-intrinsic-goals","path":"monobeast/minigrid/monobeast_amigo.py","file_url":"https://github.com/facebookresearch/adversarially-motivated-intrinsic-goals/blob/HEAD/monobeast/minigrid/monobeast_amigo.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"6189aef0d2a9d6aa","mcp_get_code":{"code_sha256":"6189aef0d2a9d6aa"}},{"arxiv_id":"1910.08210","paper":"/paper/rtfm-generalising-to-novel-environment","title":"RTFM: Generalising to Novel Environment Dynamics via Reading","date":"2019-10-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"code_sha256_prefix":"6189aef0d2a9d6aa","mcp_get_code":{"code_sha256":"6189aef0d2a9d6aa"}},{"arxiv_id":"1910.03552","paper":"/paper/torchbeast-a-pytorch-platform-for-distributed","title":"TorchBeast: A PyTorch Platform for Distributed RL","date":"2019-10-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"code_sha256_prefix":"d6d7e0906f1c57b2","mcp_get_code":{"code_sha256":"d6d7e0906f1c57b2"}},{"arxiv_id":"1809.04474","paper":"/paper/multi-task-deep-reinforcement-learning-with","title":"Multi-task Deep Reinforcement Learning with PopArt","date":"2018-09-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"aluscher/torchbeastpopart","path":"torchbeast/polybeast.py","file_url":"https://github.com/aluscher/torchbeastpopart/blob/HEAD/torchbeast/polybeast.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"fd36e71a3f45b446","mcp_get_code":{"code_sha256":"fd36e71a3f45b446"}},{"arxiv_id":"1708.04782","paper":"/paper/starcraft-ii-a-new-challenge-for","title":"StarCraft II: A New Challenge for Reinforcement Learning","date":"2017-08-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"nicoladainese96/SC2-RL","path":"monobeast.py","file_url":"https://github.com/nicoladainese96/SC2-RL/blob/HEAD/monobeast.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"fa62aa3ffdea8919","mcp_get_code":{"code_sha256":"fa62aa3ffdea8919"}}]}