{"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/policynetwork","entry":"PolicyNetwork","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":7,"n_papers_ran":6,"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":8,"n_samples_ran":7,"n_samples_fingerprinted":3,"n_places":8,"n_places_pointer_only":5,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":7,"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":"2605.14297","paper":"/paper/arxiv-2605-14297","title":"Policy Optimization in Hybrid Discrete-Continuous Action Spaces via Mixed Gradients","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"MatiasAlvo/hybrid-rl","path":"src/algorithms/hybrid/agents/hybrid_agent.py","file_url":"https://github.com/MatiasAlvo/hybrid-rl/blob/HEAD/src/algorithms/hybrid/agents/hybrid_agent.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2b850180e713db47","mcp_get_code":{"code_sha256":"2b850180e713db47"}},{"arxiv_id":"2502.17109","paper":"/paper/strength-estimation-and-human-like-strength","title":"Strength Estimation and Human-Like Strength Adjustment in Games","date":"2025-02-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rlglab/strength-estimator","path":"strength/trainer/bt_network.py","file_url":"https://github.com/rlglab/strength-estimator/blob/HEAD/strength/trainer/bt_network.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"code_sha256_prefix":"139d149a8b6d4718","mcp_get_code":{"code_sha256":"139d149a8b6d4718"}},{"arxiv_id":"2502.16634","paper":"/paper/optionzero-planning-with-learned-options","title":"OptionZero: Planning with Learned Options","date":"2025-02-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rlglab/optionzero","path":"minizero/network/py/muzero_atari_network.py","file_url":"https://github.com/rlglab/optionzero/blob/HEAD/minizero/network/py/muzero_atari_network.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"345160ccdcdb2d64","mcp_get_code":{"code_sha256":"345160ccdcdb2d64"}},{"arxiv_id":"2311.07178","paper":"/paper/game-solving-with-online-fine-tuning","title":"Game Solving with Online Fine-Tuning","date":"2023-11-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rlglab/online-fine-tuning-solver","path":"game_solver/trainer/learner/proof_cost_network.py","file_url":"https://github.com/rlglab/online-fine-tuning-solver/blob/HEAD/game_solver/trainer/learner/proof_cost_network.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"cc17d07fb0cb9a1c","mcp_get_code":{"code_sha256":"cc17d07fb0cb9a1c"}},{"arxiv_id":"2211.03413","paper":"/paper/max-min-off-policy-actor-critic-method","title":"Max-Min Off-Policy Actor-Critic Method Focusing on Worst-Case Robustness to Model Misspecification","date":"2022-11-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"akimotolab/m2td3","path":"M2TD3/m2td3.py","file_url":"https://github.com/akimotolab/m2td3/blob/HEAD/M2TD3/m2td3.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"1c8bfc04604f3ab4","mcp_get_code":{"code_sha256":"1c8bfc04604f3ab4"}},{"arxiv_id":"1802.06070","paper":"/paper/diversity-is-all-you-need-learning-skills","title":"Diversity is All You Need: Learning Skills without a Reward Function","date":"2018-02-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"alirezakazemipour/DIAYN-PyTorch","path":"Brain/agent.py","file_url":"https://github.com/alirezakazemipour/DIAYN-PyTorch/blob/HEAD/Brain/agent.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f94f400f8198fffa","mcp_get_code":{"code_sha256":"f94f400f8198fffa"}},{"arxiv_id":"1801.01290","paper":"/paper/soft-actor-critic-off-policy-maximum-entropy","title":"Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor","date":"2018-01-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"quantumiracle/Popular-RL-Algorithms","path":"sac_v2.py","file_url":"https://github.com/quantumiracle/Popular-RL-Algorithms/blob/HEAD/sac_v2.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"540316788d2c30c7","mcp_get_code":{"code_sha256":"540316788d2c30c7"}},{"arxiv_id":"1801.01290","paper":"/paper/soft-actor-critic-off-policy-maximum-entropy","title":"Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor","date":"2018-01-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ajaysub110/rl-pytorch","path":"sac/models/soft_actor_critic.py","file_url":"https://github.com/ajaysub110/rl-pytorch/blob/HEAD/sac/models/soft_actor_critic.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"ec7050db6c32a43a","mcp_get_code":{"code_sha256":"ec7050db6c32a43a"}}]}