{"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/explorative-imitation-learning-a-path","title":"Explorative Imitation Learning: A Path Signature Approach for Continuous Environments","arxiv_id":"2407.04856","date":"2024-07-05","proceeding":null,"authors":["Nathan Gavenski","Juarez Monteiro","Felipe Meneguzzi","Michael Luck","Odinaldo Rodrigues"],"abstract":"Some imitation learning methods combine behavioural cloning with self-supervision to infer actions from state pairs. However, most rely on a large number of expert trajectories to increase generalisation and human intervention to capture key aspects of the problem, such as domain constraints. In this paper, we propose Continuous Imitation Learning from Observation (CILO), a new method augmenting imitation learning with two important features: (i) exploration, allowing for more diverse state transitions, requiring less expert trajectories and resulting in fewer training iterations; and (ii) path signatures, allowing for automatic encoding of constraints, through the creation of non-parametric representations of agents and expert trajectories. We compared CILO with a baseline and two leading imitation learning methods in five environments. It had the best overall performance of all methods in all environments, outperforming the expert in two of them.","url_abs":"https://arxiv.org/abs/2407.04856v2","url_pdf":"https://arxiv.org/pdf/2407.04856v2.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":"explorative-imitation-learning-a-path","repo_url":"https://github.com/NathanGavenski/CILO","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"explorative-imitation-learning-a-path","repo_url":"https://github.com/nathangavenski/il-datasets","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"behavioural-cloning","task_name":"Behavioural cloning"},{"task_slug":"imitation-learning","task_name":"Imitation Learning"}],"methods":[{"method_slug":"cilo","method_name":"CILO"}],"datasets_introduced":[],"methods_introduced":[{"slug":"cilo","name":"CILO","full_name":"Continuous Imitation Learning from Observation"}],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2407.04856","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.04856"}},"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/nathangavenski/il-datasets","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/NathanGavenski/CILO","reach":null}],"summary":{"ran_violates":1,"ran_honours":1},"by_repo_kind":{"official":{"samples":1,"ran":1,"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":2,"samples":[{"code_sha256_prefix":"a58bd8b2eab49e87","entry":"create_data_file","repo":"NathanGavenski/CILO","repo_kind":"official","path":"create_dataset_mujoco.py","file_url":"https://github.com/NathanGavenski/CILO/blob/HEAD/create_dataset_mujoco.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a58bd8b2eab49e87"}},{"code_sha256_prefix":"7337f1f5ff01dcd0","entry":"get_lr","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"7337f1f5ff01dcd0"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}