{"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/an-empirical-investigation-of-representation","title":"An Empirical Investigation of Representation Learning for Imitation","arxiv_id":"2205.07886","date":"2022-05-16","proceeding":null,"authors":["Xin Chen","Sam Toyer","Cody Wild","Scott Emmons","Ian Fischer","Kuang-Huei Lee","Neel Alex","Steven H Wang","Ping Luo","Stuart Russell","Pieter Abbeel","Rohin Shah"],"abstract":"Imitation learning often needs a large demonstration set in order to handle the full range of situations that an agent might find itself in during deployment. However, collecting expert demonstrations can be expensive. Recent work in vision, reinforcement learning, and NLP has shown that auxiliary representation learning objectives can reduce the need for large amounts of expensive, task-specific data. Our Empirical Investigation of Representation Learning for Imitation (EIRLI) investigates whether similar benefits apply to imitation learning. We propose a modular framework for constructing representation learning algorithms, then use our framework to evaluate the utility of representation learning for imitation across several environment suites. In the settings we evaluate, we find that existing algorithms for image-based representation learning provide limited value relative to a well-tuned baseline with image augmentations. To explain this result, we investigate differences between imitation learning and other settings where representation learning has provided significant benefit, such as image classification. Finally, we release a well-documented codebase which both replicates our findings and provides a modular framework for creating new representation learning algorithms out of reusable components.","url_abs":"https://arxiv.org/abs/2205.07886v1","url_pdf":"https://arxiv.org/pdf/2205.07886v1.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":"an-empirical-investigation-of-representation","repo_url":"https://github.com/humancompatibleai/eirli","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"an-empirical-investigation-of-representation","repo_url":"https://github.com/humancompatibleai/il-representations","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"imitation-learning","task_name":"Imitation Learning"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2205.07886","atlas_url":"https://app.syntology.ai/?focus=2205.07886","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.07886"}},"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/humancompatibleai/il-representations","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/humancompatibleai/eirli","reach":null}],"summary":{"ran_draft_wrong":1,"ran_violates":1},"by_repo_kind":{"official":{"samples":2,"ran":2,"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":"b78de4e96e204812","entry":"get_default_args","repo":"humancompatibleai/eirli","repo_kind":"official","path":"src/il_representations/algos/representation_learner.py","file_url":"https://github.com/humancompatibleai/eirli/blob/HEAD/src/il_representations/algos/representation_learner.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b78de4e96e204812"}},{"code_sha256_prefix":"0f86bccccfbb58a6","entry":"to_dict","repo":"humancompatibleai/eirli","repo_kind":"official","path":"src/il_representations/algos/representation_learner.py","file_url":"https://github.com/humancompatibleai/eirli/blob/HEAD/src/il_representations/algos/representation_learner.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"0f86bccccfbb58a6"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}