{"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/choose-action","entry":"choose_action","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":6,"n_papers_ran":2,"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":6,"n_samples_ran":2,"n_samples_fingerprinted":1,"n_places":7,"n_places_pointer_only":6,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":1,"ran":1,"unverified":4},"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":"2405.07838","paper":"/paper/adaptive-exploration-for-data-efficient","title":"Adaptive Exploration for Data-Efficient General Value Function Evaluations","date":"2024-05-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"arushijain94/gvfexplorer","path":"VarianceReduction/src/BPI.py","file_url":"https://github.com/arushijain94/gvfexplorer/blob/HEAD/VarianceReduction/src/BPI.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"79b9dd785d50a15e","mcp_get_code":{"code_sha256":"79b9dd785d50a15e"}},{"arxiv_id":"2405.07838","paper":"/paper/adaptive-exploration-for-data-efficient","title":"Adaptive Exploration for Data-Efficient General Value Function Evaluations","date":"2024-05-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"arushijain94/explorationofgvfs","path":"VarianceReduction/src/bpg.py","file_url":"https://github.com/arushijain94/explorationofgvfs/blob/HEAD/VarianceReduction/src/bpg.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"74d545a970aaee61","mcp_get_code":{"code_sha256":"74d545a970aaee61"}},{"arxiv_id":"2312.06436","paper":"/paper/reward-certification-for-policy-smoothed","title":"Reward Certification for Policy Smoothed Reinforcement Learning","date":"2023-12-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"trustai/receps","path":"Cartpole/cart-train-action-smoot.py","file_url":"https://github.com/trustai/receps/blob/HEAD/Cartpole/cart-train-action-smoot.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"0effa27eababf646","mcp_get_code":{"code_sha256":"0effa27eababf646"}},{"arxiv_id":"2301.01609","paper":"/paper/emergent-collective-intelligence-from-massive","title":"Emergent collective intelligence from massive-agent cooperation and competition","date":"2023-01-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hanmochen/lux-open","path":"agent/agent.py","file_url":"https://github.com/hanmochen/lux-open/blob/HEAD/agent/agent.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"84f00eb8f9eff6dd","mcp_get_code":{"code_sha256":"84f00eb8f9eff6dd"}},{"arxiv_id":"1706.10295","paper":"/paper/noisy-networks-for-exploration","title":"Noisy Networks for Exploration","date":"2017-06-30","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":"2bd713d31dc46902","mcp_get_code":{"code_sha256":"2bd713d31dc46902"}},{"arxiv_id":"1602.01783","paper":"/paper/asynchronous-methods-for-deep-reinforcement","title":"Asynchronous Methods for Deep Reinforcement Learning","date":"2016-02-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"miyosuda/async_deep_reinforce","path":"a3c_display.py","file_url":"https://github.com/miyosuda/async_deep_reinforce/blob/HEAD/a3c_display.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":"21cd096f7f260710","mcp_get_code":{"code_sha256":"21cd096f7f260710"}},{"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":"MOVzeroOne/DQN","path":"src/run_model.py","file_url":"https://github.com/MOVzeroOne/DQN/blob/HEAD/src/run_model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"2bd713d31dc46902","mcp_get_code":{"code_sha256":"2bd713d31dc46902"}}]}