{"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/hybrid-reinforcement-learning-with-expert","title":"Hybrid Reinforcement Learning with Expert State Sequences","arxiv_id":"1903.04110","date":"2019-03-11","proceeding":null,"authors":["Xiaoxiao Guo","Shiyu Chang","Mo Yu","Gerald Tesauro","Murray Campbell"],"abstract":"Existing imitation learning approaches often require that the complete\ndemonstration data, including sequences of actions and states, are available.\nIn this paper, we consider a more realistic and difficult scenario where a\nreinforcement learning agent only has access to the state sequences of an\nexpert, while the expert actions are unobserved. We propose a novel\ntensor-based model to infer the unobserved actions of the expert state\nsequences. The policy of the agent is then optimized via a hybrid objective\ncombining reinforcement learning and imitation learning. We evaluated our\nhybrid approach on an illustrative domain and Atari games. The empirical\nresults show that (1) the agents are able to leverage state expert sequences to\nlearn faster than pure reinforcement learning baselines, (2) our tensor-based\naction inference model is advantageous compared to standard deep neural\nnetworks in inferring expert actions, and (3) the hybrid policy optimization\nobjective is robust against noise in expert state sequences.","url_abs":"http://arxiv.org/abs/1903.04110v1","url_pdf":"http://arxiv.org/pdf/1903.04110v1.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":"hybrid-reinforcement-learning-with-expert","repo_url":"https://github.com/XiaoxiaoGuo/tensor4rl","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"atari-games","task_name":"Atari Games"},{"task_slug":"imitation-learning","task_name":"Imitation Learning"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1903.04110","atlas_url":"https://app.syntology.ai/?focus=1903.04110","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1903.04110"}},"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/XiaoxiaoGuo/tensor4rl","reach":{"status":"ok","spdx":"MIT"}}],"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":"6aff48ec0d1463e1","entry":"compute_cov_a","repo":"XiaoxiaoGuo/tensor4rl","repo_kind":"official","path":"algo/kfac.py","file_url":"https://github.com/XiaoxiaoGuo/tensor4rl/blob/HEAD/algo/kfac.py","link_basis":"harvester_set","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":"6aff48ec0d1463e1"}},{"code_sha256_prefix":"d9fd61d47e236b09","entry":"compute_cov_g","repo":"XiaoxiaoGuo/tensor4rl","repo_kind":"official","path":"algo/kfac.py","file_url":"https://github.com/XiaoxiaoGuo/tensor4rl/blob/HEAD/algo/kfac.py","link_basis":"harvester_set","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":"d9fd61d47e236b09"}},{"code_sha256_prefix":"5f9e60fbf29ea537","entry":"decode","repo":"XiaoxiaoGuo/tensor4rl","repo_kind":"official","path":"policies.py","file_url":"https://github.com/XiaoxiaoGuo/tensor4rl/blob/HEAD/policies.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":"5f9e60fbf29ea537"}},{"code_sha256_prefix":"ba806bf433068ec0","entry":"decode_location","repo":"XiaoxiaoGuo/tensor4rl","repo_kind":"official","path":"policies.py","file_url":"https://github.com/XiaoxiaoGuo/tensor4rl/blob/HEAD/policies.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":"ba806bf433068ec0"}},{"code_sha256_prefix":"d1c743696ec7bba1","entry":"encode","repo":"XiaoxiaoGuo/tensor4rl","repo_kind":"official","path":"policies.py","file_url":"https://github.com/XiaoxiaoGuo/tensor4rl/blob/HEAD/policies.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":"d1c743696ec7bba1"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}