{"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/lobsdice-offline-imitation-learning-from","title":"LobsDICE: Offline Learning from Observation via Stationary Distribution Correction Estimation","arxiv_id":"2202.13536","date":"2022-02-28","proceeding":null,"authors":["Geon-Hyeong Kim","Jongmin Lee","Youngsoo Jang","Hongseok Yang","Kee-Eung Kim"],"abstract":"We consider the problem of learning from observation (LfO), in which the agent aims to mimic the expert's behavior from the state-only demonstrations by experts. We additionally assume that the agent cannot interact with the environment but has access to the action-labeled transition data collected by some agents with unknown qualities. This offline setting for LfO is appealing in many real-world scenarios where the ground-truth expert actions are inaccessible and the arbitrary environment interactions are costly or risky. In this paper, we present LobsDICE, an offline LfO algorithm that learns to imitate the expert policy via optimization in the space of stationary distributions. Our algorithm solves a single convex minimization problem, which minimizes the divergence between the two state-transition distributions induced by the expert and the agent policy. Through an extensive set of offline LfO tasks, we show that LobsDICE outperforms strong baseline methods.","url_abs":"https://arxiv.org/abs/2202.13536v2","url_pdf":"https://arxiv.org/pdf/2202.13536v2.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":"lobsdice-offline-imitation-learning-from","repo_url":"https://github.com/geon-hyeong/imitation-dice","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"lobsdice-offline-imitation-learning-from","repo_url":"https://github.com/kaist-ailab/imitation-dice","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"imitation-learning","task_name":"Imitation Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2202.13536","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.13536"}},"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/geon-hyeong/imitation-dice","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/kaist-ailab/imitation-dice","reach":{"status":"ok","spdx":"Apache-2.0"}}],"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":0,"samples":[{"code_sha256_prefix":"de7dfe13ea6c9e3d","entry":"add_absorbing_states","repo":"geon-hyeong/imitation-dice","repo_kind":"official","path":"utils.py","file_url":"https://github.com/geon-hyeong/imitation-dice/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"de7dfe13ea6c9e3d"}},{"code_sha256_prefix":"3b81875ee24223a6","entry":"boolean","repo":"geon-hyeong/imitation-dice","repo_kind":"official","path":"config/lfd_default_config.py","file_url":"https://github.com/geon-hyeong/imitation-dice/blob/HEAD/config/lfd_default_config.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"3b81875ee24223a6"}},{"code_sha256_prefix":"b1c0ce2e87ab7757","entry":"check_and_normalize_box_actions","repo":"geon-hyeong/imitation-dice","repo_kind":"official","path":"wrappers/normalize_action_wrapper.py","file_url":"https://github.com/geon-hyeong/imitation-dice/blob/HEAD/wrappers/normalize_action_wrapper.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b1c0ce2e87ab7757"}},{"code_sha256_prefix":"e2cd2e34acacdb21","entry":"evaluate_d4rl","repo":"geon-hyeong/imitation-dice","repo_kind":"official","path":"lfd_mujoco.py","file_url":"https://github.com/geon-hyeong/imitation-dice/blob/HEAD/lfd_mujoco.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"e2cd2e34acacdb21"}},{"code_sha256_prefix":"8a5275eeca2fbda2","entry":"load_d4rl_data","repo":"geon-hyeong/imitation-dice","repo_kind":"official","path":"utils.py","file_url":"https://github.com/geon-hyeong/imitation-dice/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"8a5275eeca2fbda2"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}