{"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/goal-distance","entry":"goal_distance","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":3,"n_samples_ran":2,"n_samples_fingerprinted":2,"n_places":7,"n_places_pointer_only":3,"by_status":{"ran_honours":1,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":1,"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":"2403.01734","paper":"/paper/offline-goal-conditioned-reinforcement","title":"Offline Goal-Conditioned Reinforcement Learning for Safety-Critical Tasks with Recovery Policy","date":"2024-03-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sunlighted/rbsl","path":"rl_modules/base_agent.py","file_url":"https://github.com/sunlighted/rbsl/blob/HEAD/rl_modules/base_agent.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"6eb59c36d3f33fe4","mcp_get_code":{"code_sha256":"6eb59c36d3f33fe4"}},{"arxiv_id":"2402.07226","paper":"/paper/stitching-sub-trajectories-with-conditional","title":"Stitching Sub-Trajectories with Conditional Diffusion Model for Goal-Conditioned Offline RL","date":"2024-02-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rlatjddbs/ssd","path":"bc/base_agent.py","file_url":"https://github.com/rlatjddbs/ssd/blob/HEAD/bc/base_agent.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"6eb59c36d3f33fe4","mcp_get_code":{"code_sha256":"6eb59c36d3f33fe4"}},{"arxiv_id":"2305.09943","paper":"/paper/demonstration-free-autonomous-reinforcement","title":"Demonstration-free Autonomous Reinforcement Learning via Implicit and Bidirectional Curriculum","date":"2023-05-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"snu-larr/ibc_official","path":"hgg/hgg.py","file_url":"https://github.com/snu-larr/ibc_official/blob/HEAD/hgg/hgg.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"b02202bf22dda2af","mcp_get_code":{"code_sha256":"b02202bf22dda2af"}},{"arxiv_id":"2206.03023","paper":"/paper/how-far-i-ll-go-offline-goal-conditioned","title":"How Far I'll Go: Offline Goal-Conditioned Reinforcement Learning via $f$-Advantage Regression","date":"2022-06-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jasonma2016/gofar","path":"rl_modules/base_agent.py","file_url":"https://github.com/jasonma2016/gofar/blob/HEAD/rl_modules/base_agent.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"6eb59c36d3f33fe4","mcp_get_code":{"code_sha256":"6eb59c36d3f33fe4"}},{"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/fetch_env.py","file_url":"https://github.com/anyboby/mujoco_safety_gym/blob/HEAD/mujoco_safety_gym/envs/fetch_env.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"6eb59c36d3f33fe4","mcp_get_code":{"code_sha256":"6eb59c36d3f33fe4"}},{"arxiv_id":"1905.13402","paper":"/paper/extending-deep-model-predictive-control-with","title":"Safety Augmented Value Estimation from Demonstrations (SAVED): Safe Deep Model-Based RL for Sparse Cost Robotic Tasks","date":"2019-05-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"harryzhangOG/salved","path":"dmbrl/env/fetch_env.py","file_url":"https://github.com/harryzhangOG/salved/blob/HEAD/dmbrl/env/fetch_env.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b692c1c9edaeb844","mcp_get_code":{"code_sha256":"b692c1c9edaeb844"}},{"arxiv_id":"1806.07851","paper":"/paper/sim-to-real-reinforcement-learning-for","title":"Sim-to-Real Reinforcement Learning for Deformable Object Manipulation","date":"2018-06-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"JanMatas/Rainbow_ddpg","path":"micoenv/mico_robot_env.py","file_url":"https://github.com/JanMatas/Rainbow_ddpg/blob/HEAD/micoenv/mico_robot_env.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"6eb59c36d3f33fe4","mcp_get_code":{"code_sha256":"6eb59c36d3f33fe4"}}]}