{"url":"/task/model-based-reinforcement-learning","name":"Model-based Reinforcement Learning","slug":"model-based-reinforcement-learning","description_markdown":null,"categories":[{"name":"Methodology","url":"/area/methodology"},{"name":"Playing Games","url":"/area/playing-games"},{"name":"Reasoning","url":"/area/reasoning"},{"name":"Robots","url":"/area/robots"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":708,"papers_with_code":234,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":1,"subtasks":0,"parent_tasks":1},"benchmarks":[],"datasets":[{"url":"/dataset/popgym","name":"POPGym","full_name":"Partially Observable Process Gym","num_papers_in_archive":3}],"subtasks":[],"parent_tasks":[{"url":"/task/general-reinforcement-learning","name":"General Reinforcement Learning"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":234,"tagged_in_all":708,"items":[{"url":"/paper/when-to-trust-your-model-model-based-policy","title":"When to Trust Your Model: Model-Based Policy Optimization","date":"2019-06-19","arxiv_id":"1906.08253","repositories_listed":11,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":3}},{"url":"/paper/deep-reinforcement-learning-in-a-handful-of","title":"Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models","date":"2018-05-30","arxiv_id":"1805.12114","repositories_listed":9,"syntology":{"n":19,"n_ran":12,"n_unverified":7,"n_pointer_only":17}},{"url":"/paper/neural-network-dynamics-for-model-based-deep","title":"Neural Network Dynamics for Model-Based Deep Reinforcement Learning with Model-Free Fine-Tuning","date":"2017-08-08","arxiv_id":"1708.02596","repositories_listed":9,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":2}},{"url":"/paper/td-mpc2-scalable-robust-world-models-for","title":"TD-MPC2: Scalable, Robust World Models for Continuous Control","date":"2023-10-25","arxiv_id":"2310.16828","repositories_listed":3,"syntology":{"n":16,"n_ran":12,"n_unverified":4,"n_pointer_only":0}},{"url":"/paper/trafficbots-towards-world-models-for","title":"TrafficBots: Towards World Models for Autonomous Driving Simulation and Motion Prediction","date":"2023-03-07","arxiv_id":"2303.04116","repositories_listed":3,"syntology":null},{"url":"/paper/planning-with-diffusion-for-flexible-behavior","title":"Planning with Diffusion for Flexible Behavior Synthesis","date":"2022-05-20","arxiv_id":"2205.09991","repositories_listed":3,"syntology":null},{"url":"/paper/temporal-predictive-coding-for-model-based","title":"Temporal Predictive Coding For Model-Based Planning In Latent Space","date":"2021-06-14","arxiv_id":"2106.07156","repositories_listed":3,"syntology":{"n":9,"n_ran":2,"n_unverified":7,"n_pointer_only":0}},{"url":"/paper/integrated-decision-and-control-towards","title":"Integrated Decision and Control: Towards Interpretable and Computationally Efficient Driving Intelligence","date":"2021-03-18","arxiv_id":"2103.10290","repositories_listed":3,"syntology":null},{"url":"/paper/a-model-based-reinforcement-learning-with","title":"Model-Based Reinforcement Learning with Adversarial Training for Online Recommendation","date":"2019-11-10","arxiv_id":"1911.03845","repositories_listed":3,"syntology":{"n":2,"n_ran":1,"n_unverified":1,"n_pointer_only":2}},{"url":"/paper/dynamics-aware-unsupervised-discovery-of","title":"Dynamics-Aware Unsupervised Discovery of Skills","date":"2019-07-02","arxiv_id":"1907.01657","repositories_listed":3,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/machine-learning-and-system-identification","title":"Machine Learning and System Identification for Estimation in Physical Systems","date":"2019-06-05","arxiv_id":"1906.02003","repositories_listed":3,"syntology":null},{"url":"/paper/pipps-flexible-model-based-policy-search","title":"PIPPS: Flexible Model-Based Policy Search Robust to the Curse of Chaos","date":"2019-02-04","arxiv_id":"1902.01240","repositories_listed":3,"syntology":null},{"url":"/paper/synthesizing-neural-network-controllers-with","title":"Synthesizing Neural Network Controllers with Probabilistic Model based Reinforcement Learning","date":"2018-03-06","arxiv_id":"1803.02291","repositories_listed":3,"syntology":null},{"url":"/paper/model-based-reinforcement-learning-for-7","title":"Model-based Reinforcement Learning for Parameterized Action Spaces","date":"2024-04-03","arxiv_id":"2404.03037","repositories_listed":2,"syntology":{"n":9,"n_ran":9,"n_unverified":0,"n_pointer_only":9}},{"url":"/paper/the-edge-of-reach-problem-in-offline-model","title":"The Edge-of-Reach Problem in Offline Model-Based Reinforcement Learning","date":"2024-02-19","arxiv_id":"2402.12527","repositories_listed":2,"syntology":null},{"url":"/paper/language-agent-tree-search-unifies-reasoning","title":"Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Models","date":"2023-10-06","arxiv_id":"2310.04406","repositories_listed":2,"syntology":{"n":9,"n_ran":7,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/predictive-experience-replay-for-continual","title":"Predictive Experience Replay for Continual Visual Control and Forecasting","date":"2023-03-12","arxiv_id":"2303.06572","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/predictable-mdp-abstraction-for-unsupervised","title":"Predictable MDP Abstraction for Unsupervised Model-Based RL","date":"2023-02-08","arxiv_id":"2302.03921","repositories_listed":2,"syntology":null},{"url":"/paper/the-surprising-effectiveness-of-latent-world","title":"The Effectiveness of World Models for Continual Reinforcement Learning","date":"2022-11-29","arxiv_id":"2211.15944","repositories_listed":2,"syntology":null},{"url":"/paper/an-experimental-design-perspective-on-model","title":"An Experimental Design Perspective on Model-Based Reinforcement Learning","date":"2021-12-09","arxiv_id":"2112.05244","repositories_listed":2,"syntology":{"n":4,"n_ran":4,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/gradient-information-matters-in-policy","title":"Gradient Information Matters in Policy Optimization by Back-propagating through Model","date":"2021-09-29","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/planning-in-stochastic-environments-with-a","title":"Planning in Stochastic Environments with a Learned Model","date":"2021-09-29","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/mbrl-lib-a-modular-library-for-model-based","title":"MBRL-Lib: A Modular Library for Model-based Reinforcement Learning","date":"2021-04-20","arxiv_id":"2104.10159","repositories_listed":2,"syntology":null},{"url":"/paper/online-and-offline-reinforcement-learning-by","title":"Online and Offline Reinforcement Learning by Planning with a Learned Model","date":"2021-04-13","arxiv_id":"2104.06294","repositories_listed":2,"syntology":null},{"url":"/paper/bellman-a-toolbox-for-model-based","title":"Bellman: A Toolbox for Model-Based Reinforcement Learning in TensorFlow","date":"2021-03-26","arxiv_id":"2103.14407","repositories_listed":2,"syntology":null},{"url":"/paper/improving-model-based-reinforcement-learning","title":"Improving Model-Based Reinforcement Learning with Internal State Representations through Self-Supervision","date":"2021-02-10","arxiv_id":"2102.05599","repositories_listed":2,"syntology":null},{"url":"/paper/beyond-prioritized-replay-sampling-states-in","title":"Understanding and Mitigating the Limitations of Prioritized Experience Replay","date":"2020-07-19","arxiv_id":"2007.09569","repositories_listed":2,"syntology":null},{"url":"/paper/the-loca-regret-a-consistent-metric-to","title":"The LoCA Regret: A Consistent Metric to Evaluate Model-Based Behavior in Reinforcement Learning","date":"2020-07-07","arxiv_id":"2007.03158","repositories_listed":2,"syntology":{"n":2,"n_ran":1,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/context-aware-dynamics-model-for","title":"Context-aware Dynamics Model for Generalization in Model-Based Reinforcement Learning","date":"2020-05-14","arxiv_id":"2005.06800","repositories_listed":2,"syntology":{"n":3,"n_ran":2,"n_unverified":1,"n_pointer_only":2}},{"url":"/paper/objective-mismatch-in-model-based-1","title":"Objective Mismatch in Model-based Reinforcement Learning","date":"2020-02-11","arxiv_id":"2002.04523","repositories_listed":2,"syntology":null}],"syntology_records":13,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}