{"total":159,"rows":[{"id":"2103.06257","title":"Maximum Entropy RL (Provably) Solves Some Robust RL Problems","created":"2021-03-10","cited_by_count":176,"area":null},{"id":"2111.09794","title":"A Survey of Zero-shot Generalisation in Deep Reinforcement Learning","created":"2021-11-18","cited_by_count":170,"area":null},{"id":"2107.00541","title":"Goal-Conditioned Reinforcement Learning with Imagined Subgoals","created":"2021-07-01","cited_by_count":134,"area":null},{"id":"2304.13653","title":"Learning Agile Soccer Skills for a Bipedal Robot with Deep Reinforcement Learning","created":"2023-04-26","cited_by_count":133,"area":null},{"id":"2110.02034","title":"Dropout Q-Functions for Doubly Efficient Reinforcement Learning","created":"2021-10-05","cited_by_count":114,"area":null},{"id":"2105.13231","title":"AndroidEnv: A Reinforcement Learning Platform for Android","created":"2021-05-27","cited_by_count":90,"area":null},{"id":"2105.12196","title":"From Motor Control to Team Play in Simulated Humanoid Football","created":"2021-05-25","cited_by_count":87,"area":null},{"id":"2106.00661","title":"Reward is enough for convex MDPs","created":"2021-06-01","cited_by_count":84,"area":null},{"id":"2102.01585","title":"Approximately Solving Mean Field Games via Entropy-Regularized Deep Reinforcement Learning","created":"2021-02-02","cited_by_count":73,"area":null},{"id":"2306.00186","title":"Factually Consistent Summarization via Reinforcement Learning with Textual Entailment Feedback","created":"2023-05-31","cited_by_count":72,"area":null},{"id":"2110.06192","title":"Beyond Pick-and-Place: Tackling Robotic Stacking of Diverse Shapes","created":"2021-10-12","cited_by_count":71,"area":null},{"id":"2201.11927","title":"Constrained Variational Policy Optimization for Safe Reinforcement Learning","created":"2022-01-28","cited_by_count":71,"area":null},{"id":"2204.08957","title":"COptiDICE: Offline Constrained Reinforcement Learning via Stationary Distribution Correction Estimation","created":"2022-04-19","cited_by_count":71,"area":null},{"id":"2405.10315","title":"TRANSIC: Sim-to-Real Policy Transfer by Learning from Online Correction","created":"2024-05-16","cited_by_count":59,"area":null},{"id":"2106.03787","title":"Concave Utility Reinforcement Learning: the Mean-Field Game Viewpoint","created":"2021-06-07","cited_by_count":56,"area":null},{"id":"2104.06159","title":"Muesli: Combining Improvements in Policy Optimization","created":"2021-04-13","cited_by_count":53,"area":null},{"id":"2109.04504","title":"Bootstrapped Meta-Learning","created":"2021-09-09","cited_by_count":45,"area":null},{"id":"2210.04932","title":"NeRF2Real: Sim2real Transfer of Vision-guided Bipedal Motion Skills using Neural Radiance Fields","created":"2022-10-10","cited_by_count":44,"area":null},{"id":"2102.05261","title":"Simple Agent, Complex Environment: Efficient Reinforcement Learning with Agent States","created":"2021-02-10","cited_by_count":43,"area":null},{"id":"2107.08285","title":"Greedification Operators for Policy Optimization: Investigating Forward and Reverse KL Divergences","created":"2021-07-17","cited_by_count":41,"area":null},{"id":"2102.11938","title":"Baby Intuitions Benchmark (BIB): Discerning the goals, preferences, and actions of others","created":"2021-02-23","cited_by_count":39,"area":null},{"id":"2104.01655","title":"Efficient Transformers in Reinforcement Learning using Actor-Learner Distillation","created":"2021-04-04","cited_by_count":35,"area":null},{"id":"2206.00484","title":"DEP-RL: Embodied Exploration for Reinforcement Learning in Overactuated and Musculoskeletal Systems","created":"2022-05-30","cited_by_count":29,"area":null},{"id":"2209.08466","title":"Simplifying Model-based RL: Learning Representations, Latent-space Models, and Policies with One Objective","created":"2022-09-18","cited_by_count":28,"area":null},{"id":"2112.05062","title":"Learning Transferable Motor Skills with Hierarchical Latent Mixture Policies","created":"2021-12-09","cited_by_count":26,"area":null},{"id":"2101.09207","title":"Differentiable Trust Region Layers for Deep Reinforcement Learning","created":"2021-01-22","cited_by_count":25,"area":null},{"id":"2210.08863","title":"You Only Live Once: Single-Life Reinforcement Learning","created":"2022-10-17","cited_by_count":24,"area":null},{"id":"2210.12566","title":"Solving Continuous Control via Q-learning","created":"2022-10-22","cited_by_count":24,"area":null},{"id":"2508.12511","title":"Trust Region Constrained Measure Transport in Path Space for Stochastic Optimal Control and Inference","created":"2025-08-17","cited_by_count":23,"area":null},{"id":"2102.13176","title":"A Probabilistic Interpretation of Self-Paced Learning with Applications to Reinforcement Learning","created":"2021-02-25","cited_by_count":22,"area":null},{"id":"2109.14311","title":"Learning Dynamics Models for Model Predictive Agents","created":"2021-09-29","cited_by_count":22,"area":null},{"id":"2203.04051","title":"Robot Learning of Mobile Manipulation with Reachability Behavior Priors","created":"2022-03-08","cited_by_count":22,"area":null},{"id":"2302.01275","title":"ReLOAD: Reinforcement Learning with Optimistic Ascent-Descent for Last-Iterate Convergence in Constrained MDPs","created":"2023-02-02","cited_by_count":20,"area":null},{"id":"2206.04672","title":"Overcoming the Spectral Bias of Neural Value Approximation","created":"2022-06-09","cited_by_count":19,"area":null},{"id":"2102.12611","title":"Improved Regret Bound and Experience Replay in Regularized Policy Iteration","created":"2021-02-25","cited_by_count":18,"area":null},{"id":"2108.05828","title":"A general class of surrogate functions for stable and efficient reinforcement learning","created":"2021-08-12","cited_by_count":18,"area":null},{"id":"2310.03718","title":"Constraint-Conditioned Policy Optimization for Versatile Safe Reinforcement Learning","created":"2023-10-05","cited_by_count":18,"area":null},{"id":"2108.10273","title":"Collect & Infer -- a fresh look at data-efficient Reinforcement Learning","created":"2021-08-23","cited_by_count":17,"area":null},{"id":"2306.09466","title":"Simplified Temporal Consistency Reinforcement Learning","created":"2023-06-15","cited_by_count":17,"area":null},{"id":"2205.15460","title":"Critic Sequential Monte Carlo","created":"2022-05-30","cited_by_count":16,"area":null},{"id":"2301.11721","title":"Single-Trajectory Distributionally Robust Reinforcement Learning","created":"2023-01-27","cited_by_count":16,"area":null},{"id":"2103.12726","title":"Policy Information Capacity: Information-Theoretic Measure for Task Complexity in Deep Reinforcement Learning","created":"2021-03-23","cited_by_count":15,"area":null},{"id":"2103.17258","title":"Co-Adaptation of Algorithmic and Implementational Innovations in Inference-based Deep Reinforcement Learning","created":"2021-03-31","cited_by_count":15,"area":null},{"id":"2110.03363","title":"Evaluating model-based planning and planner amortization for continuous control","created":"2021-10-07","cited_by_count":15,"area":null},{"id":"2212.09010","title":"Risk-Sensitive Reinforcement Learning with Exponential Criteria","created":"2022-12-18","cited_by_count":15,"area":null},{"id":"2101.09458","title":"Decoupled Exploration and Exploitation Policies for Sample-Efficient Reinforcement Learning","created":"2021-01-23","cited_by_count":14,"area":null},{"id":"2109.08603","title":"Is Curiosity All You Need? On the Utility of Emergent Behaviours from Curious Exploration","created":"2021-09-17","cited_by_count":14,"area":null},{"id":"2202.07415","title":"NeuPL: Neural Population Learning","created":"2022-02-15","cited_by_count":14,"area":null},{"id":"2110.11280","title":"Actor-critic is implicitly biased towards high entropy optimal policies","created":"2021-10-21","cited_by_count":13,"area":null},{"id":"2206.08736","title":"Generalised Policy Improvement with Geometric Policy Composition","created":"2022-06-17","cited_by_count":13,"area":null},{"id":"2209.10081","title":"Revisiting Discrete Soft Actor-Critic","created":"2022-09-21","cited_by_count":13,"area":null},{"id":"2210.00999","title":"Latent State Marginalization as a Low-cost Approach for Improving Exploration","created":"2022-10-03","cited_by_count":13,"area":null},{"id":"2210.02317","title":"Real-Time Reinforcement Learning for Vision-Based Robotics Utilizing Local and Remote Computers","created":"2022-10-05","cited_by_count":13,"area":null},{"id":"2301.12593","title":"Risk-Averse Model Uncertainty for Distributionally Robust Safe Reinforcement Learning","created":"2023-01-30","cited_by_count":12,"area":null},{"id":"2110.04686","title":"Braxlines: Fast and Interactive Toolkit for RL-driven Behavior Engineering beyond Reward Maximization","created":"2021-10-10","cited_by_count":11,"area":null},{"id":"2211.03413","title":"Max-Min Off-Policy Actor-Critic Method Focusing on Worst-Case Robustness to Model Misspecification","created":"2022-11-07","cited_by_count":11,"area":null},{"id":"2311.13294","title":"Probabilistic Inference in Reinforcement Learning Done Right","created":"2023-11-22","cited_by_count":11,"area":null},{"id":"2102.06234","title":"Optimization Issues in KL-Constrained Approximate Policy Iteration","created":"2021-02-11","cited_by_count":10,"area":null},{"id":"2103.06859","title":"Understanding the Origin of Information-Seeking Exploration in Probabilistic Objectives for Control","created":"2021-03-11","cited_by_count":10,"area":null},{"id":"2203.16707","title":"Monte Carlo Tree Search based Hybrid Optimization of Variational Quantum Circuits","created":"2022-03-30","cited_by_count":10,"area":null},{"id":"2209.01947","title":"MO2: Model-Based Offline Options","created":"2022-09-05","cited_by_count":10,"area":null},{"id":"2302.09339","title":"Efficient Exploration via Epistemic-Risk-Seeking Policy Optimization","created":"2023-02-18","cited_by_count":10,"area":null},{"id":"2311.15951","title":"Replay across Experiments: A Natural Extension of Off-Policy RL","created":"2023-11-27","cited_by_count":10,"area":null},{"id":"2106.05526","title":"Simplifying Deep Reinforcement Learning via Self-Supervision","created":"2021-06-10","cited_by_count":9,"area":null},{"id":"2107.00140","title":"Applications of the Free Energy Principle to Machine Learning and Neuroscience","created":"2021-06-30","cited_by_count":9,"area":null},{"id":"2108.07041","title":"Implicitly Regularized RL with Implicit Q-Values","created":"2021-08-16","cited_by_count":9,"area":null},{"id":"2203.00715","title":"Learning Robust Real-Time Cultural Transmission without Human Data","created":"2022-03-01","cited_by_count":9,"area":null},{"id":"2207.13131","title":"Semi-analytical Industrial Cooling System Model for Reinforcement Learning","created":"2022-07-26","cited_by_count":9,"area":null},{"id":"2301.13375","title":"Optimal Transport Perturbations for Safe Reinforcement Learning with Robustness Guarantees","created":"2023-01-31","cited_by_count":9,"area":null},{"id":"2307.11546","title":"Towards practical reinforcement learning for tokamak magnetic control","created":"2023-07-21","cited_by_count":9,"area":null},{"id":"2510.18460","title":"Learning Boltzmann Generators via Constrained Mass Transport","created":"2025-10-21","cited_by_count":9,"area":null},{"id":"2102.04881","title":"Measuring Progress in Deep Reinforcement Learning Sample Efficiency","created":"2021-02-09","cited_by_count":8,"area":null},{"id":"2108.07783","title":"Toward a `Standard Model' of Machine Learning","created":"2021-08-17","cited_by_count":8,"area":null},{"id":"2111.02994","title":"Towards an Understanding of Default Policies in Multitask Policy Optimization","created":"2021-11-04","cited_by_count":8,"area":null},{"id":"2202.03957","title":"Bingham Policy Parameterization for 3D Rotations in Reinforcement Learning","created":"2022-02-08","cited_by_count":8,"area":null},{"id":"2205.15879","title":"Simplex Neural Population Learning: Any-Mixture Bayes-Optimality in Symmetric Zero-sum Games","created":"2022-05-31","cited_by_count":8,"area":null},{"id":"2312.11091","title":"Colored Noise in PPO: Improved Exploration and Performance through Correlated Action Sampling","created":"2023-12-18","cited_by_count":8,"area":null},{"id":"2103.01009","title":"Snowflake: Scaling GNNs to High-Dimensional Continuous Control via Parameter Freezing","created":"2021-03-01","cited_by_count":7,"area":null},{"id":"2106.02613","title":"Bridging the Gap Between Target Networks and Functional Regularization","created":"2021-06-04","cited_by_count":7,"area":null},{"id":"2110.12840","title":"Self-Consistent Models and Values","created":"2021-10-25","cited_by_count":7,"area":null},{"id":"2510.03817","title":"TROLL: Trust Regions improve Reinforcement Learning for Large Language Models","created":"2025-10-04","cited_by_count":7,"area":null},{"id":"2107.09088","title":"Reward-Weighted Regression Converges to a Global Optimum","created":"2021-07-19","cited_by_count":6,"area":null},{"id":"2201.12434","title":"Do You Need the Entropy Reward (in Practice)?","created":"2022-01-28","cited_by_count":6,"area":null},{"id":"2204.10256","title":"Revisiting Gaussian mixture critics in off-policy reinforcement learning: a sample-based approach","created":"2022-04-21","cited_by_count":6,"area":null},{"id":"2207.03952","title":"Learning with Muscles: Benefits for Data-Efficiency and Robustness in Anthropomorphic Tasks","created":"2022-07-08","cited_by_count":6,"area":null},{"id":"2211.13743","title":"SkillS: Adaptive Skill Sequencing for Efficient Temporally-Extended Exploration","created":"2022-11-24","cited_by_count":6,"area":null},{"id":"2302.12617","title":"Leveraging Jumpy Models for Planning and Fast Learning in Robotic Domains","created":"2023-02-24","cited_by_count":6,"area":null},{"id":"2306.14133","title":"Provably Convergent Policy Optimization via Metric-aware Trust Region Methods","created":"2023-06-25","cited_by_count":6,"area":null},{"id":"2310.19527","title":"On the Theory of Risk-Aware Agents: Bridging Actor-Critic and Economics","created":"2023-10-30","cited_by_count":6,"area":null},{"id":"2204.05893","title":"Forgetting and Imbalance in Robot Lifelong Learning with Off-policy Data","created":"2022-04-12","cited_by_count":5,"area":null},{"id":"2209.07676","title":"Conservative Dual Policy Optimization for Efficient Model-Based Reinforcement Learning","created":"2022-09-16","cited_by_count":5,"area":null},{"id":"2402.07963","title":"SPO: Sequential Monte Carlo Policy Optimisation","created":"2024-02-12","cited_by_count":5,"area":null},{"id":"2505.20578","title":"Ctrl-DNA: Controllable Cell-Type-Specific Regulatory DNA Design via Constrained RL","created":"2025-05-26","cited_by_count":5,"area":null},{"id":"2102.06782","title":"Q-Value Weighted Regression: Reinforcement Learning with Limited Data","created":"2021-02-12","cited_by_count":4,"area":null},{"id":"2201.07286","title":"Conservative Distributional Reinforcement Learning with Safety Constraints","created":"2022-01-18","cited_by_count":4,"area":null},{"id":"2204.09315","title":"Learning to Constrain Policy Optimization with Virtual Trust Region","created":"2022-04-20","cited_by_count":4,"area":null},{"id":"2206.02544","title":"RLSS: A Deep Reinforcement Learning Algorithm for Sequential Scene Generation","created":"2022-06-01","cited_by_count":4,"area":null},{"id":"2209.12347","title":"Opportunities and Challenges from Using Animal Videos in Reinforcement Learning for Navigation","created":"2022-09-25","cited_by_count":4,"area":null},{"id":"2311.01953","title":"Optimistic Multi-Agent Policy Gradient","created":"2023-11-03","cited_by_count":4,"area":null},{"id":"2401.05133","title":"Neural Population Learning beyond Symmetric Zero-sum Games","created":"2024-01-10","cited_by_count":4,"area":null}],"next_cursor":"100"}