{"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":"/paper/imitating-graph-based-planning-with-goal","title":"Imitating Graph-Based Planning with Goal-Conditioned Policies","arxiv_id":"2303.11166","date":"2023-03-20","proceeding":null,"authors":["Junsu Kim","Younggyo Seo","Sungsoo Ahn","Kyunghwan Son","Jinwoo Shin"],"abstract":"Recently, graph-based planning algorithms have gained much attention to solve goal-conditioned reinforcement learning (RL) tasks: they provide a sequence of subgoals to reach the target-goal, and the agents learn to execute subgoal-conditioned policies. However, the sample-efficiency of such RL schemes still remains a challenge, particularly for long-horizon tasks. To address this issue, we present a simple yet effective self-imitation scheme which distills a subgoal-conditioned policy into the target-goal-conditioned policy. Our intuition here is that to reach a target-goal, an agent should pass through a subgoal, so target-goal- and subgoal- conditioned policies should be similar to each other. We also propose a novel scheme of stochastically skipping executed subgoals in a planned path, which further improves performance. Unlike prior methods that only utilize graph-based planning in an execution phase, our method transfers knowledge from a planner along with a graph into policy learning. We empirically show that our method can significantly boost the sample-efficiency of the existing goal-conditioned RL methods under various long-horizon control tasks.","url_abs":"https://arxiv.org/abs/2303.11166v1","url_pdf":"https://arxiv.org/pdf/2303.11166v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"imitating-graph-based-planning-with-goal","repo_url":"https://github.com/junsu-kim97/pig","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2303.11166","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.11166"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/junsu-kim97/pig","reach":null}],"summary":{"ran_draft_wrong":1,"ran_violates":1,"unverified":2},"by_repo_kind":{"official":{"samples":4,"ran":2,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"5681f154e63b1f30","entry":"farthest_point_sample","repo":"junsu-kim97/pig","repo_kind":"official","path":"planner/goal_plan.py","file_url":"https://github.com/junsu-kim97/pig/blob/HEAD/planner/goal_plan.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5681f154e63b1f30"}},{"code_sha256_prefix":"b92d018d6cbdd419","entry":"transform","repo":"junsu-kim97/pig","repo_kind":"official","path":"planner/goal_plan.py","file_url":"https://github.com/junsu-kim97/pig/blob/HEAD/planner/goal_plan.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b92d018d6cbdd419"}},{"code_sha256_prefix":"0e14c1538dc4b9b2","entry":"Planner","repo":"junsu-kim97/pig","repo_kind":"official","path":"planner/goal_plan.py","file_url":"https://github.com/junsu-kim97/pig/blob/HEAD/planner/goal_plan.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0e14c1538dc4b9b2"}},{"code_sha256_prefix":"f84995c51788ed77","entry":"get_env_params","repo":"junsu-kim97/pig","repo_kind":"official","path":"train_ddpg.py","file_url":"https://github.com/junsu-kim97/pig/blob/HEAD/train_ddpg.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f84995c51788ed77"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}