{"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/learning-world-models-for-unconstrained-goal","title":"Learning World Models for Unconstrained Goal Navigation","arxiv_id":"2411.02446","date":"2024-11-03","proceeding":null,"authors":["Yuanlin Duan","Wensen Mao","He Zhu"],"abstract":"Learning world models offers a promising avenue for goal-conditioned reinforcement learning with sparse rewards. By allowing agents to plan actions or exploratory goals without direct interaction with the environment, world models enhance exploration efficiency. The quality of a world model hinges on the richness of data stored in the agent's replay buffer, with expectations of reasonable generalization across the state space surrounding recorded trajectories. However, challenges arise in generalizing learned world models to state transitions backward along recorded trajectories or between states across different trajectories, hindering their ability to accurately model real-world dynamics. To address these challenges, we introduce a novel goal-directed exploration algorithm, MUN (short for \"World Models for Unconstrained Goal Navigation\"). This algorithm is capable of modeling state transitions between arbitrary subgoal states in the replay buffer, thereby facilitating the learning of policies to navigate between any \"key\" states. Experimental results demonstrate that MUN strengthens the reliability of world models and significantly improves the policy's capacity to generalize across new goal settings.","url_abs":"https://arxiv.org/abs/2411.02446v1","url_pdf":"https://arxiv.org/pdf/2411.02446v1.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":"learning-world-models-for-unconstrained-goal","repo_url":"https://github.com/RU-Automated-Reasoning-Group/MUN","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"navigate","task_name":"Navigate"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2411.02446","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.02446"}},"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/RU-Automated-Reasoning-Group/MUN","reach":{"status":"ok"}}],"summary":{"unverified":5},"by_repo_kind":{"official":{"samples":5,"ran":0,"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":5,"samples":[{"code_sha256_prefix":"8f39adcc1afcac90","entry":"get_act","repo":"RU-Automated-Reasoning-Group/MUN","repo_kind":"official","path":"dreamerv2_APS/common/nets.py","file_url":"https://github.com/RU-Automated-Reasoning-Group/MUN/blob/HEAD/dreamerv2_APS/common/nets.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"8f39adcc1afcac90"}},{"code_sha256_prefix":"e3bdc0207b89292d","entry":"get_actor_inp","repo":"RU-Automated-Reasoning-Group/MUN","repo_kind":"official","path":"dreamerv2_APS/gc_agent.py","file_url":"https://github.com/RU-Automated-Reasoning-Group/MUN/blob/HEAD/dreamerv2_APS/gc_agent.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e3bdc0207b89292d"}},{"code_sha256_prefix":"5f26af0c0a474816","entry":"get_future_goal_idxs","repo":"RU-Automated-Reasoning-Group/MUN","repo_kind":"official","path":"dreamerv2_APS/gc_agent.py","file_url":"https://github.com/RU-Automated-Reasoning-Group/MUN/blob/HEAD/dreamerv2_APS/gc_agent.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"5f26af0c0a474816"}},{"code_sha256_prefix":"abd4dbc14ca35f32","entry":"get_future_goal_idxs_neg_sampling","repo":"RU-Automated-Reasoning-Group/MUN","repo_kind":"official","path":"dreamerv2_APS/gc_agent.py","file_url":"https://github.com/RU-Automated-Reasoning-Group/MUN/blob/HEAD/dreamerv2_APS/gc_agent.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"abd4dbc14ca35f32"}},{"code_sha256_prefix":"29f0fc44eda255b5","entry":"softmax","repo":"RU-Automated-Reasoning-Group/MUN","repo_kind":"official","path":"dreamerv2_APS/gc_goal_picker.py","file_url":"https://github.com/RU-Automated-Reasoning-Group/MUN/blob/HEAD/dreamerv2_APS/gc_goal_picker.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"29f0fc44eda255b5"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}