{"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/zero-shot-offline-imitation-learning-via","title":"Zero-Shot Offline Imitation Learning via Optimal Transport","arxiv_id":"2410.08751","date":"2024-10-11","proceeding":null,"authors":["Thomas Rupf","Marco Bagatella","Nico Gürtler","Jonas Frey","Georg Martius"],"abstract":"Zero-shot imitation learning algorithms hold the promise of reproducing unseen behavior from as little as a single demonstration at test time. Existing practical approaches view the expert demonstration as a sequence of goals, enabling imitation with a high-level goal selector, and a low-level goal-conditioned policy. However, this framework can suffer from myopic behavior: the agent's immediate actions towards achieving individual goals may undermine long-term objectives. We introduce a novel method that mitigates this issue by directly optimizing the occupancy matching objective that is intrinsic to imitation learning. We propose to lift a goal-conditioned value function to a distance between occupancies, which are in turn approximated via a learned world model. The resulting method can learn from offline, suboptimal data, and is capable of non-myopic, zero-shot imitation, as we demonstrate in complex, continuous benchmarks.","url_abs":"https://arxiv.org/abs/2410.08751v1","url_pdf":"https://arxiv.org/pdf/2410.08751v1.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":"zero-shot-offline-imitation-learning-via","repo_url":"https://github.com/martius-lab/zilot","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"jax","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"imitation-learning","task_name":"Imitation Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2410.08751","atlas_url":"https://app.syntology.ai/?focus=2410.08751","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.08751"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/martius-lab/zilot","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":6,"unverified":1},"by_repo_kind":{"official":{"samples":7,"ran":6,"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":"1ce7b1b39fad990b","entry":"add_done_masks","repo":"martius-lab/zilot","repo_kind":"official","path":"zilot/common/buffer.py","file_url":"https://github.com/martius-lab/zilot/blob/HEAD/zilot/common/buffer.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":"1ce7b1b39fad990b"}},{"code_sha256_prefix":"37df8a6e41f37f85","entry":"comp_log_std","repo":"martius-lab/zilot","repo_kind":"official","path":"zilot/model/tdmpc2.py","file_url":"https://github.com/martius-lab/zilot/blob/HEAD/zilot/model/tdmpc2.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":"37df8a6e41f37f85"}},{"code_sha256_prefix":"027dc57646ce7fa2","entry":"gaussian_logprob","repo":"martius-lab/zilot","repo_kind":"official","path":"zilot/model/tdmpc2.py","file_url":"https://github.com/martius-lab/zilot/blob/HEAD/zilot/model/tdmpc2.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":"027dc57646ce7fa2"}},{"code_sha256_prefix":"12d7dffc9978ba0d","entry":"gc_value_to_steps","repo":"martius-lab/zilot","repo_kind":"official","path":"zilot/model/util.py","file_url":"https://github.com/martius-lab/zilot/blob/HEAD/zilot/model/util.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"12d7dffc9978ba0d"}},{"code_sha256_prefix":"cad2da135c7b87f7","entry":"mlp","repo":"martius-lab/zilot","repo_kind":"official","path":"zilot/model/curious.py","file_url":"https://github.com/martius-lab/zilot/blob/HEAD/zilot/model/curious.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":"cad2da135c7b87f7"}},{"code_sha256_prefix":"928642d6998fafb2","entry":"soft_ce","repo":"martius-lab/zilot","repo_kind":"official","path":"zilot/model/tdmpc2.py","file_url":"https://github.com/martius-lab/zilot/blob/HEAD/zilot/model/tdmpc2.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":"928642d6998fafb2"}},{"code_sha256_prefix":"2c5481376eb91faa","entry":"parse_cfg","repo":"martius-lab/zilot","repo_kind":"official","path":"zilot/parse.py","file_url":"https://github.com/martius-lab/zilot/blob/HEAD/zilot/parse.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":"2c5481376eb91faa"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}