{"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/backward-learning-for-goal-conditioned","title":"Backward Learning for Goal-Conditioned Policies","arxiv_id":"2312.05044","date":"2023-12-08","proceeding":null,"authors":["Marc Höftmann","Jan Robine","Stefan Harmeling"],"abstract":"Can we learn policies in reinforcement learning without rewards? Can we learn a policy just by trying to reach a goal state? We answer these questions positively by proposing a multi-step procedure that first learns a world model that goes backward in time, secondly generates goal-reaching backward trajectories, thirdly improves those sequences using shortest path finding algorithms, and finally trains a neural network policy by imitation learning. We evaluate our method on a deterministic maze environment where the observations are $64\\times 64$ pixel bird's eye images and can show that it consistently reaches several goals.","url_abs":"https://arxiv.org/abs/2312.05044v2","url_pdf":"https://arxiv.org/pdf/2312.05044v2.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":"backward-learning-for-goal-conditioned","repo_url":"https://github.com/hauf3n/backward-learning-for-goal-conditioned-policies","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"imitation-learning","task_name":"Imitation Learning"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2312.05044","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.05044"}},"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":"deterministic:regex_extraction","url":"https://github.com/Hauf3n/Backward-Learning-for-Goal-Conditioned-Policies","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/hauf3n/backward-learning-for-goal-conditioned-policies","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":5,"unverified":4},"by_repo_kind":{"official":{"samples":9,"ran":5,"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":"d6de9591bc5121a4","entry":"BWM","repo":"hauf3n/backward-learning-for-goal-conditioned-policies","repo_kind":"official","path":"networks/world_model.py","file_url":"https://github.com/hauf3n/backward-learning-for-goal-conditioned-policies/blob/HEAD/networks/world_model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d6de9591bc5121a4"}},{"code_sha256_prefix":"7e52ed7d12d46448","entry":"collect_data","repo":"Hauf3n/Backward-Learning-for-Goal-Conditioned-Policies","repo_kind":"official","path":"data_env/environments.py","file_url":"https://github.com/Hauf3n/Backward-Learning-for-Goal-Conditioned-Policies/blob/HEAD/data_env/environments.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7e52ed7d12d46448"}},{"code_sha256_prefix":"777f25d4930be7e3","entry":"dream","repo":"Hauf3n/Backward-Learning-for-Goal-Conditioned-Policies","repo_kind":"official","path":"data_env/dream_env.py","file_url":"https://github.com/Hauf3n/Backward-Learning-for-Goal-Conditioned-Policies/blob/HEAD/data_env/dream_env.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"777f25d4930be7e3"}},{"code_sha256_prefix":"f86f4a5c521a1b8a","entry":"join_txt","repo":"Hauf3n/Backward-Learning-for-Goal-Conditioned-Policies","repo_kind":"official","path":"goals/sde.py","file_url":"https://github.com/Hauf3n/Backward-Learning-for-Goal-Conditioned-Policies/blob/HEAD/goals/sde.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f86f4a5c521a1b8a"}},{"code_sha256_prefix":"f378cc0c2725550e","entry":"read_dict_from_file","repo":"Hauf3n/Backward-Learning-for-Goal-Conditioned-Policies","repo_kind":"official","path":"utill/util_arguments.py","file_url":"https://github.com/Hauf3n/Backward-Learning-for-Goal-Conditioned-Policies/blob/HEAD/utill/util_arguments.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f378cc0c2725550e"}},{"code_sha256_prefix":"bef57747905820da","entry":"draw_evaluated_policy_multigoal_rgb","repo":"Hauf3n/Backward-Learning-for-Goal-Conditioned-Policies","repo_kind":"official","path":"data_env/environments.py","file_url":"https://github.com/Hauf3n/Backward-Learning-for-Goal-Conditioned-Policies/blob/HEAD/data_env/environments.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":"bef57747905820da"}},{"code_sha256_prefix":"ee6a82fd09305a4f","entry":"draw_evaluated_policy_rgb","repo":"Hauf3n/Backward-Learning-for-Goal-Conditioned-Policies","repo_kind":"official","path":"data_env/environments.py","file_url":"https://github.com/Hauf3n/Backward-Learning-for-Goal-Conditioned-Policies/blob/HEAD/data_env/environments.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":"ee6a82fd09305a4f"}},{"code_sha256_prefix":"1c0eef6485fba686","entry":"init_modify_wandb","repo":"Hauf3n/Backward-Learning-for-Goal-Conditioned-Policies","repo_kind":"official","path":"utill/util_arguments.py","file_url":"https://github.com/Hauf3n/Backward-Learning-for-Goal-Conditioned-Policies/blob/HEAD/utill/util_arguments.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":"1c0eef6485fba686"}},{"code_sha256_prefix":"efefe1330a38b67a","entry":"learn_policy","repo":"Hauf3n/Backward-Learning-for-Goal-Conditioned-Policies","repo_kind":"official","path":"goals/learn_policy.py","file_url":"https://github.com/Hauf3n/Backward-Learning-for-Goal-Conditioned-Policies/blob/HEAD/goals/learn_policy.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":"efefe1330a38b67a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}