{"list":"other","total":54,"rows":[{"id":"2106.01946","title":"Convex optimization","created":"2021-06-03","cited_by_count":2515},{"id":"1506.02438","title":"High-Dimensional Continuous Control Using Generalized Advantage Estimation","created":"2015-06-08","cited_by_count":2026},{"id":"2005.01643","title":"Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems","created":"2020-05-04","cited_by_count":1920},{"id":"2006.04779","title":"Conservative Q-Learning for Offline Reinforcement Learning","created":"2020-06-08","cited_by_count":1809},{"id":"1705.10528","title":"Constrained Policy Optimization","created":"2017-05-30","cited_by_count":983},{"id":"1910.09457","title":"Aleatoric and Epistemic Uncertainty in Machine Learning: An Introduction to Concepts and Methods","created":"2019-10-21","cited_by_count":913},{"id":"1507.06527","title":"Deep Recurrent Q-Learning for Partially Observable MDPs","created":"2015-07-23","cited_by_count":465},{"id":"1708.08611","title":"Safe Reinforcement Learning via Shielding","created":"2017-08-29","cited_by_count":449},{"id":"2012.15085","title":"Is Pessimism Provably Efficient for Offline RL?","created":"2020-12-30","cited_by_count":364},{"id":"1512.01629","title":"Risk-Constrained Reinforcement Learning with Percentile Risk Criteria","created":"2015-12-05","cited_by_count":337},{"id":"2103.06257","title":"Maximum Entropy RL (Provably) Solves Some Robust RL Problems","created":"2021-03-10","cited_by_count":176},{"id":"2107.06226","title":"Pessimistic Model-based Offline Reinforcement Learning under Partial Coverage","created":"2021-07-13","cited_by_count":164},{"id":"1705.01292","title":"A General Safety Framework for Learning-Based Control in Uncertain Robotic Systems","created":"2017-05-03","cited_by_count":163},{"id":"1712.03632","title":"Robust Deep Reinforcement Learning with Adversarial Attacks","created":"2017-12-11","cited_by_count":154},{"id":"1712.06924","title":"Safe Policy Improvement with Baseline Bootstrapping","created":"2017-12-19","cited_by_count":144},{"id":"2208.05129","title":"Robust Reinforcement Learning using Offline Data","created":"2022-08-10","cited_by_count":96},{"id":"2006.14389","title":"Reinforcement Learning for Non-Stationary Markov Decision Processes: The Blessing of (More) Optimism","created":"2020-06-24","cited_by_count":76},{"id":"1905.09638","title":"Estimating Risk and Uncertainty in Deep Reinforcement Learning","created":"2019-05-23","cited_by_count":70},{"id":"1802.04412","title":"Efficient Exploration through Bayesian Deep Q-Networks","created":"2018-02-13","cited_by_count":67},{"id":"2102.05371","title":"Risk-Averse Offline Reinforcement Learning","created":"2021-02-10","cited_by_count":65},{"id":"2201.09802","title":"Constrained Policy Optimization via Bayesian World Models","created":"2022-01-24","cited_by_count":57},{"id":"2204.00755","title":"Safe Reinforcement Learning via Shielding under Partial Observability","created":"2022-04-02","cited_by_count":56},{"id":"1607.03842","title":"Safe Policy Improvement by Minimizing Robust Baseline Regret","created":"2016-07-13","cited_by_count":53},{"id":"1902.07605","title":"Beyond Confidence Regions: Tight Bayesian Ambiguity Sets for Robust MDPs","created":"2019-02-20","cited_by_count":40},{"id":"2006.16712","title":"Model-based Reinforcement Learning: A Survey","created":"2020-06-30","cited_by_count":39},{"id":"1905.04403","title":"PAC Statistical Model Checking for Markov Decision Processes and Stochastic Games","created":"2019-05-10","cited_by_count":32},{"id":"2112.12228","title":"Direct Behavior Specification via Constrained Reinforcement Learning","created":"2021-12-22","cited_by_count":31},{"id":"1805.10066","title":"A Sliding-Window Algorithm for Markov Decision Processes with Arbitrarily Changing Rewards and Transitions","created":"2018-05-25","cited_by_count":30},{"id":"2007.07176","title":"Robustifying Reinforcement Learning Agents via Action Space Adversarial Training","created":"2020-07-14","cited_by_count":30},{"id":"2102.05762","title":"Risk-Averse Bayes-Adaptive Reinforcement Learning","created":"2021-02-10","cited_by_count":29},{"id":"1301.6720","title":"Solving POMDPs by Searching the Space of Finite Policies","created":"2013-01-23","cited_by_count":26},{"id":"1811.00215","title":"Robust Markov Decision Process: Beyond Rectangularity","created":"2018-11-01","cited_by_count":24},{"id":"2009.11459","title":"Robust Finite-State Controllers for Uncertain POMDPs","created":"2020-09-24","cited_by_count":24},{"id":"1907.05079","title":"Safe Policy Improvement with Soft Baseline Bootstrapping","created":"2019-07-11","cited_by_count":22},{"id":"2101.07491","title":"Automated Verification and Synthesis of Stochastic Hybrid Systems: A Survey","created":"2021-01-19","cited_by_count":20},{"id":"2105.09452","title":"Minimum-Delay Adaptation in Non-Stationary Reinforcement Learning via Online High-Confidence Change-Point Detection","created":"2021-05-20","cited_by_count":18},{"id":"1909.05236","title":"Safe Policy Improvement with an Estimated Baseline Policy","created":"2019-09-11","cited_by_count":17},{"id":"2205.15827","title":"Robust Anytime Learning of Markov Decision Processes","created":"2022-05-31","cited_by_count":16},{"id":"2301.01526","title":"Robust Control for Dynamical Systems With Non-Gaussian Noise via Formal Abstractions","created":"2023-01-04","cited_by_count":16},{"id":"1811.05612","title":"Bayesian Reinforcement Learning in Factored POMDPs","created":"2018-11-14","cited_by_count":15},{"id":"1309.2802","title":"What is Decidable about Partially Observable Markov Decision Processes with {\\omega}-Regular Objectives","created":"2013-09-11","cited_by_count":14},{"id":"1405.4733","title":"Multiple-Environment Markov Decision Processes","created":"2014-05-19","cited_by_count":13},{"id":"1901.10287","title":"StocHy: automated verification and synthesis of stochastic processes","created":"2019-01-29","cited_by_count":13},{"id":"2110.12662","title":"Sampling-Based Robust Control of Autonomous Systems with Non-Gaussian Noise","created":"2021-10-25","cited_by_count":13},{"id":"1602.04875","title":"POMDP-lite for Robust Robot Planning under Uncertainty","created":"2016-02-16","cited_by_count":12},{"id":"2301.04939","title":"Safe Policy Improvement for POMDPs via Finite-State Controllers","created":"2023-01-12","cited_by_count":12},{"id":"2210.05989","title":"Probabilities Are Not Enough: Formal Controller Synthesis for Stochastic Dynamical Models with Epistemic Uncertainty","created":"2022-10-12","cited_by_count":11},{"id":"2112.13020","title":"Scenario-Based Verification of Uncertain Parametric MDPs","created":"2021-12-24","cited_by_count":8},{"id":"2206.14402","title":"Constructing MDP Abstractions Using Data with Formal Guarantees","created":"2022-06-29","cited_by_count":7},{"id":"1503.03715","title":"Feedback Refinement Relations for the Synthesis of Symbolic Controllers","created":"2015-03-12","cited_by_count":6},{"id":"1903.08428","title":"Counterexample-Guided Strategy Improvement for POMDPs Using Recurrent Neural Networks","created":"2019-03-20","cited_by_count":6},{"id":"2103.02398","title":"Correct-by-construction reach-avoid control of partially observable linear stochastic systems","created":"2021-03-03","cited_by_count":5},{"id":"2205.08300","title":"Sampling-Based Verification of CTMCs with Uncertain Rates","created":"2022-05-17","cited_by_count":5},{"id":"2006.14923","title":"Approximating Euclidean by Imprecise Markov Decision Processes","created":"2020-06-26","cited_by_count":4}],"next_cursor":null}