{"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/mass-center","entry":"mass_center","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":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":3,"n_samples_ran":1,"n_samples_fingerprinted":0,"n_places":8,"n_places_pointer_only":3,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":1,"unverified":2},"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":"2606.12896","paper":"/paper/arxiv-2606-12896","title":"PolicyGuard: Towards Test-time and Step-level Adversary (Backdoor) Defense for Reinforcement Learning Agent","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"openai/multiagent-competition","path":"gym-compete/gym_compete/new_envs/agents/ant_fighter.py","file_url":"https://github.com/openai/multiagent-competition/blob/HEAD/gym-compete/gym_compete/new_envs/agents/ant_fighter.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"2aaf6c2bab400d9c","mcp_get_code":{"code_sha256":"2aaf6c2bab400d9c"}},{"arxiv_id":"2405.16390","paper":"/paper/safe-and-balanced-a-framework-for-constrained","title":"Safe and Balanced: A Framework for Constrained Multi-Objective Reinforcement Learning","date":"2024-05-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"SafeRL-Lab/Safe-Multi-Objective-MuJoCo","path":"safe-mo-mujoco/humanoid_v4.py","file_url":"https://github.com/SafeRL-Lab/Safe-Multi-Objective-MuJoCo/blob/HEAD/safe-mo-mujoco/humanoid_v4.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"15f107f303a8f1fc","mcp_get_code":{"code_sha256":"15f107f303a8f1fc"}},{"arxiv_id":"2405.01677","paper":"/paper/balance-reward-and-safety-optimization-for","title":"Balance Reward and Safety Optimization for Safe Reinforcement Learning: A Perspective of Gradient Manipulation","date":"2024-05-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"saferl-lab/safety-mujoco","path":"safety_mujoco/humanoid_v4.py","file_url":"https://github.com/saferl-lab/safety-mujoco/blob/HEAD/safety_mujoco/humanoid_v4.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"15f107f303a8f1fc","mcp_get_code":{"code_sha256":"15f107f303a8f1fc"}},{"arxiv_id":"2212.00124","paper":"/paper/one-risk-to-rule-them-all-a-risk-sensitive-1","title":"One Risk to Rule Them All: A Risk-Sensitive Perspective on Model-Based Offline Reinforcement Learning","date":"2022-11-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"marc-rigter/1R2R","path":"_1R2R/env/humanoid.py","file_url":"https://github.com/marc-rigter/1R2R/blob/HEAD/_1R2R/env/humanoid.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"46bd205700c42f20","mcp_get_code":{"code_sha256":"46bd205700c42f20"}},{"arxiv_id":"2110.02793","paper":"/paper/multi-agent-constrained-policy-optimisation","title":"Multi-Agent Constrained Policy Optimisation","date":"2021-10-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"chauncygu/safe-multi-agent-mujoco","path":"safety_multi_agent_mujoco/safety_ma_mujoco/safety_multiagent_mujoco/humanoid.py","file_url":"https://github.com/chauncygu/safe-multi-agent-mujoco/blob/HEAD/safety_multi_agent_mujoco/safety_ma_mujoco/safety_multiagent_mujoco/humanoid.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"46bd205700c42f20","mcp_get_code":{"code_sha256":"46bd205700c42f20"}},{"arxiv_id":"2104.06922","paper":"/paper/safe-continuous-control-with-constrained","title":"Safe Continuous Control with Constrained Model-Based Policy Optimization","date":"2021-04-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"anyboby/mujoco_safety_gym","path":"mujoco_safety_gym/envs/humanoid.py","file_url":"https://github.com/anyboby/mujoco_safety_gym/blob/HEAD/mujoco_safety_gym/envs/humanoid.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"46bd205700c42f20","mcp_get_code":{"code_sha256":"46bd205700c42f20"}},{"arxiv_id":"2103.13842","paper":"/paper/model-predictive-actor-critic-accelerating","title":"Model Predictive Actor-Critic: Accelerating Robot Skill Acquisition with Deep Reinforcement Learning","date":"2021-03-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dnandha/mopac","path":"mopac/env/humanoid.py","file_url":"https://github.com/dnandha/mopac/blob/HEAD/mopac/env/humanoid.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"46bd205700c42f20","mcp_get_code":{"code_sha256":"46bd205700c42f20"}},{"arxiv_id":"2006.13916","paper":"/paper/off-dynamics-reinforcement-learning-training","title":"Off-Dynamics Reinforcement Learning: Training for Transfer with Domain Classifiers","date":"2020-06-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"JannerM/mbpo","path":"mbpo/env/humanoid.py","file_url":"https://github.com/JannerM/mbpo/blob/HEAD/mbpo/env/humanoid.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"46bd205700c42f20","mcp_get_code":{"code_sha256":"46bd205700c42f20"}}]}