{"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/exponential-family-model-based-reinforcement","title":"Exponential Family Model-Based Reinforcement Learning via Score Matching","arxiv_id":"2112.14195","date":"2021-12-28","proceeding":null,"authors":["Gene Li","Junbo Li","Anmol Kabra","Nathan Srebro","Zhaoran Wang","Zhuoran Yang"],"abstract":"We propose an optimistic model-based algorithm, dubbed SMRL, for finite-horizon episodic reinforcement learning (RL) when the transition model is specified by exponential family distributions with $d$ parameters and the reward is bounded and known. SMRL uses score matching, an unnormalized density estimation technique that enables efficient estimation of the model parameter by ridge regression. Under standard regularity assumptions, SMRL achieves $\\tilde O(d\\sqrt{H^3T})$ online regret, where $H$ is the length of each episode and $T$ is the total number of interactions (ignoring polynomial dependence on structural scale parameters).","url_abs":"https://arxiv.org/abs/2112.14195v2","url_pdf":"https://arxiv.org/pdf/2112.14195v2.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":"exponential-family-model-based-reinforcement","repo_url":"https://github.com/anmolkabra/score-matching-rl","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"density-estimation","task_name":"Density Estimation"},{"task_slug":"model-based-reinforcement-learning","task_name":"Model-based Reinforcement Learning"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"regression-1","task_name":"regression"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2112.14195","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.14195"}},"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/anmolkabra/score-matching-rl","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":4},"by_repo_kind":{"official":{"samples":4,"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":"2e28c4d3306dabfc","entry":"batch_jacobian","repo":"anmolkabra/score-matching-rl","repo_kind":"official","path":"utils.py","file_url":"https://github.com/anmolkabra/score-matching-rl/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":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2e28c4d3306dabfc"}},{"code_sha256_prefix":"fa15f6bd402dcb40","entry":"plot_sampled_points","repo":"anmolkabra/score-matching-rl","repo_kind":"official","path":"utils_1d_densities.py","file_url":"https://github.com/anmolkabra/score-matching-rl/blob/HEAD/utils_1d_densities.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":"fa15f6bd402dcb40"}},{"code_sha256_prefix":"839970bb0c9504d6","entry":"to_numpy","repo":"anmolkabra/score-matching-rl","repo_kind":"official","path":"utils.py","file_url":"https://github.com/anmolkabra/score-matching-rl/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":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"839970bb0c9504d6"}},{"code_sha256_prefix":"36152863f9516d46","entry":"to_torch","repo":"anmolkabra/score-matching-rl","repo_kind":"official","path":"utils.py","file_url":"https://github.com/anmolkabra/score-matching-rl/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":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"36152863f9516d46"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}