{"list":"other","total":57,"rows":[{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"1801.01290","title":"Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor","created":"2018-01-04","cited_by_count":4885},{"id":"1506.02142","title":"Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning","created":"2015-06-06","cited_by_count":4448},{"id":"1612.01474","title":"Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles","created":"2016-12-05","cited_by_count":3926},{"id":"1509.02971","title":"Continuous control with deep reinforcement learning","created":"2015-09-09","cited_by_count":3407},{"id":"1802.09477","title":"Addressing Function Approximation Error in Actor-Critic Methods","created":"2018-02-26","cited_by_count":2417},{"id":"1602.01783","title":"Asynchronous Methods for Deep Reinforcement Learning","created":"2016-02-04","cited_by_count":2258},{"id":"1906.02530","title":"Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shift","created":"2019-06-06","cited_by_count":1287},{"id":"2301.04104","title":"Mastering Diverse Domains through World Models","created":"2023-01-10","cited_by_count":1253},{"id":"1705.05363","title":"Curiosity-driven Exploration by Self-supervised Prediction","created":"2017-05-15","cited_by_count":1194},{"id":"1810.12894","title":"Exploration by Random Network Distillation","created":"2018-10-30","cited_by_count":993},{"id":"1801.00690","title":"DeepMind Control Suite","created":"2018-01-02","cited_by_count":956},{"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":"2011.06225","title":"A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challenges","created":"2020-11-12","cited_by_count":819},{"id":"2108.13264","title":"Deep Reinforcement Learning at the Edge of the Statistical Precipice","created":"2021-08-30","cited_by_count":807},{"id":"1606.01868","title":"Unifying Count-Based Exploration and Intrinsic Motivation","created":"2016-06-06","cited_by_count":639},{"id":"1902.02476","title":"A Simple Baseline for Bayesian Uncertainty in Deep Learning","created":"2019-02-07","cited_by_count":560},{"id":"1602.04621","title":"Deep Exploration via Bootstrapped DQN","created":"2016-02-15","cited_by_count":527},{"id":"1703.05449","title":"Minimax Regret Bounds for Reinforcement Learning","created":"2017-03-16","cited_by_count":503},{"id":"1707.02038","title":"A Tutorial on Thompson Sampling","created":"2017-07-07","cited_by_count":433},{"id":"2106.13281","title":"Brax -- A Differentiable Physics Engine for Large Scale Rigid Body Simulation","created":"2021-06-24","cited_by_count":407},{"id":"2005.05960","title":"Planning to Explore via Self-Supervised World Models","created":"2020-05-12","cited_by_count":368},{"id":"1502.05336","title":"Probabilistic Backpropagation for Scalable Learning of Bayesian Neural Networks","created":"2015-02-18","cited_by_count":295},{"id":"1904.12901","title":"Challenges of Real-World Reinforcement Learning","created":"2019-04-29","cited_by_count":291},{"id":"2101.05982","title":"Randomized Ensembled Double Q-Learning: Learning Fast Without a Model","created":"2021-01-15","cited_by_count":288},{"id":"1706.10295","title":"Noisy Networks for Exploration","created":"2017-06-30","cited_by_count":266},{"id":"1906.04161","title":"Self-Supervised Exploration via Disagreement","created":"2019-06-10","cited_by_count":265},{"id":"1703.01310","title":"Count-Based Exploration with Neural Density Models","created":"2017-03-03","cited_by_count":257},{"id":"2205.07802","title":"The Primacy Bias in Deep Reinforcement Learning","created":"2022-05-16","cited_by_count":247},{"id":"1306.0940","title":"(More) Efficient Reinforcement Learning via Posterior Sampling","created":"2013-06-04","cited_by_count":233},{"id":"1806.03335","title":"Randomized Prior Functions for Deep Reinforcement Learning","created":"2018-06-08","cited_by_count":219},{"id":"1901.10995","title":"Go-Explore: a New Approach for Hard-Exploration Problems","created":"2019-01-30","cited_by_count":212},{"id":"1812.02648","title":"Deep Reinforcement Learning and the Deadly Triad","created":"2018-12-06","cited_by_count":174},{"id":"2302.12902","title":"The Dormant Neuron Phenomenon in Deep Reinforcement Learning","created":"2023-02-24","cited_by_count":174},{"id":"2303.01486","title":"Understanding plasticity in neural networks","created":"2023-03-02","cited_by_count":174},{"id":"1403.5556","title":"Learning to Optimize via Information-Directed Sampling","created":"2014-03-21","cited_by_count":168},{"id":"1706.01905","title":"Parameter Space Noise for Exploration","created":"2017-06-06","cited_by_count":161},{"id":"2007.04938","title":"SUNRISE: A Simple Unified Framework for Ensemble Learning in Deep Reinforcement Learning","created":"2020-07-09","cited_by_count":152},{"id":"1908.03568","title":"Behaviour Suite for Reinforcement Learning","created":"2019-08-09","cited_by_count":132},{"id":"2107.08924","title":"Epistemic Neural Networks","created":"2021-07-19","cited_by_count":120},{"id":"1706.01445","title":"Batched Large-scale Bayesian Optimization in High-dimensional Spaces","created":"2017-06-05","cited_by_count":117},{"id":"1402.0635","title":"Generalization and Exploration via Randomized Value Functions","created":"2014-02-04","cited_by_count":112},{"id":"1911.00567","title":"Frequentist Regret Bounds for Randomized Least-Squares Value Iteration","created":"2019-11-01","cited_by_count":101},{"id":"1910.12807","title":"Better Exploration with Optimistic Actor-Critic","created":"2019-10-28","cited_by_count":88},{"id":"2006.08684","title":"Efficient Model-Based Reinforcement Learning through Optimistic Policy Search and Planning","created":"2020-06-15","cited_by_count":86},{"id":"1709.05380","title":"The Uncertainty Bellman Equation and Exploration","created":"2017-09-15","cited_by_count":82},{"id":"1906.11537","title":"'In-Between' Uncertainty in Bayesian Neural Networks","created":"2019-06-27","cited_by_count":80},{"id":"2502.08844","title":"MuJoCo Playground","created":"2025-02-12","cited_by_count":78},{"id":"1801.09667","title":"Information Directed Sampling and Bandits with Heteroscedastic Noise","created":"2018-01-29","cited_by_count":76},{"id":"1906.02870","title":"Worst-Case Regret Bounds for Exploration via Randomized Value Functions","created":"2019-06-07","cited_by_count":57},{"id":"1812.07544","title":"Information-Directed Exploration for Deep Reinforcement Learning","created":"2018-12-18","cited_by_count":52},{"id":"2106.07841","title":"Randomized Exploration for Reinforcement Learning with General Value Function Approximation","created":"2021-06-15","cited_by_count":49},{"id":"2006.07464","title":"Hypermodels for Exploration","created":"2020-06-12","cited_by_count":37},{"id":"1810.06530","title":"Successor Uncertainties: Exploration and Uncertainty in Temporal Difference Learning","created":"2018-10-15","cited_by_count":35},{"id":"2302.12526","title":"Model-Based Uncertainty in Value Functions","created":"2023-02-24","cited_by_count":15},{"id":"2505.19850","title":"DISCOVER: Automated Curricula for Sparse-Reward Reinforcement Learning","created":"2025-05-26","cited_by_count":12}],"next_cursor":null}