{"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/control-oriented-model-based-reinforcement","title":"Control-Oriented Model-Based Reinforcement Learning with Implicit Differentiation","arxiv_id":"2106.03273","date":"2021-06-06","proceeding":"ICML Workshop URL 2021 7","authors":["Evgenii Nikishin","Romina Abachi","Rishabh Agarwal","Pierre-Luc Bacon"],"abstract":"The shortcomings of maximum likelihood estimation in the context of model-based reinforcement learning have been highlighted by an increasing number of papers. When the model class is misspecified or has a limited representational capacity, model parameters with high likelihood might not necessarily result in high performance of the agent on a downstream control task. To alleviate this problem, we propose an end-to-end approach for model learning which directly optimizes the expected returns using implicit differentiation. We treat a value function that satisfies the Bellman optimality operator induced by the model as an implicit function of model parameters and show how to differentiate the function. We provide theoretical and empirical evidence highlighting the benefits of our approach in the model misspecification regime compared to likelihood-based methods.","url_abs":"https://arxiv.org/abs/2106.03273v1","url_pdf":"https://arxiv.org/pdf/2106.03273v1.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":"control-oriented-model-based-reinforcement","repo_url":"https://github.com/evgenii-nikishin/omd","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"jax","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"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":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2106.03273","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.03273"}},"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/evgenii-nikishin/omd","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":"1bd2d556360ac9c9","entry":"default_init","repo":"evgenii-nikishin/omd","repo_kind":"official","path":"mujoco/jax_rl/networks/common.py","file_url":"https://github.com/evgenii-nikishin/omd/blob/HEAD/mujoco/jax_rl/networks/common.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":"1bd2d556360ac9c9"}},{"code_sha256_prefix":"580e68a39efc066b","entry":"evaluate","repo":"evgenii-nikishin/omd","repo_kind":"official","path":"cartpole/utils.py","file_url":"https://github.com/evgenii-nikishin/omd/blob/HEAD/cartpole/utils.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":"580e68a39efc066b"}},{"code_sha256_prefix":"09dd14441f8afd51","entry":"evaluate","repo":"evgenii-nikishin/omd","repo_kind":"official","path":"mujoco/jax_rl/evaluation.py","file_url":"https://github.com/evgenii-nikishin/omd/blob/HEAD/mujoco/jax_rl/evaluation.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":"09dd14441f8afd51"}},{"code_sha256_prefix":"7228e3fe72fe5ce1","entry":"root_solve","repo":"evgenii-nikishin/omd","repo_kind":"official","path":"cartpole/utils.py","file_url":"https://github.com/evgenii-nikishin/omd/blob/HEAD/cartpole/utils.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":"7228e3fe72fe5ce1"}},{"code_sha256_prefix":"3f2a540c4e621bac","entry":"root_solve_fwd","repo":"evgenii-nikishin/omd","repo_kind":"official","path":"cartpole/utils.py","file_url":"https://github.com/evgenii-nikishin/omd/blob/HEAD/cartpole/utils.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":"3f2a540c4e621bac"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}