{"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/primal-wasserstein-imitation-learning","title":"Primal Wasserstein Imitation Learning","arxiv_id":"2006.04678","date":"2020-06-08","proceeding":"ICLR 2021 1","authors":["Robert Dadashi","Léonard Hussenot","Matthieu Geist","Olivier Pietquin"],"abstract":"Imitation Learning (IL) methods seek to match the behavior of an agent with that of an expert. In the present work, we propose a new IL method based on a conceptually simple algorithm: Primal Wasserstein Imitation Learning (PWIL), which ties to the primal form of the Wasserstein distance between the expert and the agent state-action distributions. We present a reward function which is derived offline, as opposed to recent adversarial IL algorithms that learn a reward function through interactions with the environment, and which requires little fine-tuning. We show that we can recover expert behavior on a variety of continuous control tasks of the MuJoCo domain in a sample efficient manner in terms of agent interactions and of expert interactions with the environment. Finally, we show that the behavior of the agent we train matches the behavior of the expert with the Wasserstein distance, rather than the commonly used proxy of performance.","url_abs":"https://arxiv.org/abs/2006.04678v2","url_pdf":"https://arxiv.org/pdf/2006.04678v2.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":"primal-wasserstein-imitation-learning","repo_url":"https://github.com/google-research/google-research/tree/master/pwil","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":null},{"paper_slug":"primal-wasserstein-imitation-learning","repo_url":"https://github.com/Kaixhin/imitation-learning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"continuous-control","task_name":"Continuous Control"},{"task_slug":"imitation-learning","task_name":"Imitation Learning"},{"task_slug":"mujoco","task_name":"MuJoCo"},{"task_slug":"continuous-control","task_name":"continuous-control"}],"methods":[{"method_slug":"pwil","method_name":"PWIL"}],"datasets_introduced":[],"methods_introduced":[{"slug":"pwil","name":"PWIL","full_name":"Primal Wasserstein Imitation Learning"}],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2006.04678","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.04678"}},"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/Kaixhin/imitation-learning","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/google-research/google-research/tree/master/pwil","reach":null}],"summary":{"unverified":1},"by_repo_kind":{"official":{"samples":1,"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":"e859a0e4df7090ff","entry":"PWILRewarder","repo":"google-research/google-research","repo_kind":"official","path":"pwil/rewarder.py","file_url":"https://github.com/google-research/google-research/blob/HEAD/pwil/rewarder.py","link_basis":"first_harvest_node","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":"e859a0e4df7090ff"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}