{"list":"other","total":80,"rows":[{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"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":"1509.02971","title":"Continuous control with deep reinforcement learning","created":"2015-09-09","cited_by_count":3407},{"id":"1502.05477","title":"Trust Region Policy Optimization","created":"2015-02-19","cited_by_count":2580},{"id":"1802.09477","title":"Addressing Function Approximation Error in Actor-Critic Methods","created":"2018-02-26","cited_by_count":2417},{"id":"2106.01345","title":"Decision Transformer: Reinforcement Learning via Sequence Modeling","created":"2021-06-02","cited_by_count":1546},{"id":"1703.06907","title":"Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real World","created":"2017-03-20","cited_by_count":1498},{"id":"2001.06782","title":"Gradient Surgery for Multi-Task Learning","created":"2020-01-19","cited_by_count":1256},{"id":"1910.10897","title":"Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning","created":"2019-10-24","cited_by_count":1204},{"id":"1707.01495","title":"Hindsight Experience Replay","created":"2017-07-05","cited_by_count":1136},{"id":"1801.00690","title":"DeepMind Control Suite","created":"2018-01-02","cited_by_count":956},{"id":"1504.00702","title":"End-to-End Training of Deep Visuomotor Policies","created":"2015-04-02","cited_by_count":875},{"id":"1711.02257","title":"GradNorm: Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networks","created":"2017-11-07","cited_by_count":834},{"id":"2108.13264","title":"Deep Reinforcement Learning at the Edge of the Statistical Precipice","created":"2021-08-30","cited_by_count":807},{"id":"1906.08253","title":"When to Trust Your Model: Model-Based Policy Optimization","created":"2019-06-19","cited_by_count":773},{"id":"1707.06887","title":"A Distributional Perspective on Reinforcement Learning","created":"2017-07-21","cited_by_count":765},{"id":"1802.06070","title":"Diversity is All You Need: Learning Skills without a Reward Function","created":"2018-02-16","cited_by_count":752},{"id":"1910.07113","title":"Solving Rubik's Cube with a Robot Hand","created":"2019-10-16","cited_by_count":734},{"id":"1808.00177","title":"Learning Dexterous In-Hand Manipulation","created":"2018-08-01","cited_by_count":687},{"id":"1710.06537","title":"Sim-to-Real Transfer of Robotic Control with Dynamics Randomization","created":"2017-10-18","cited_by_count":672},{"id":"1702.08165","title":"Reinforcement Learning with Deep Energy-Based Policies","created":"2017-02-27","cited_by_count":669},{"id":"2004.13649","title":"Image Augmentation Is All You Need: Regularizing Deep Reinforcement Learning from Pixels","created":"2020-04-28","cited_by_count":585},{"id":"2109.11978","title":"Learning to Walk in Minutes Using Massively Parallel Deep Reinforcement Learning","created":"2021-09-24","cited_by_count":512},{"id":"2310.16828","title":"TD-MPC2: Scalable, Robust World Models for Continuous Control","created":"2023-10-25","cited_by_count":512},{"id":"1901.08652","title":"Learning agile and dynamic motor skills for legged robots","created":"2019-01-24","cited_by_count":504},{"id":"1611.02779","title":"RL$^2$: Fast Reinforcement Learning via Slow Reinforcement Learning","created":"2016-11-09","cited_by_count":503},{"id":"2004.14990","title":"Reinforcement Learning with Augmented Data","created":"2020-04-30","cited_by_count":468},{"id":"1611.05397","title":"Reinforcement Learning with Unsupervised Auxiliary Tasks","created":"2016-11-16","cited_by_count":404},{"id":"2107.09645","title":"Mastering Visual Continuous Control: Improved Data-Augmented Reinforcement Learning","created":"2021-07-20","cited_by_count":372},{"id":"2302.02948","title":"Efficient Online Reinforcement Learning with Offline Data","created":"2023-02-06","cited_by_count":363},{"id":"1812.02341","title":"Quantifying Generalization in Reinforcement Learning","created":"2018-12-06","cited_by_count":352},{"id":"1606.05312","title":"Successor Features for Transfer in Reinforcement Learning","created":"2016-06-16","cited_by_count":340},{"id":"2101.05982","title":"Randomized Ensembled Double Q-Learning: Learning Fast Without a Model","created":"2021-01-15","cited_by_count":288},{"id":"2103.09568","title":"A Practical Guide to Multi-Objective Reinforcement Learning and Planning","created":"2021-03-17","cited_by_count":256},{"id":"2206.07568","title":"Contrastive Learning as Goal-Conditioned Reinforcement Learning","created":"2022-06-15","cited_by_count":253},{"id":"2205.07802","title":"The Primacy Bias in Deep Reinforcement Learning","created":"2022-05-16","cited_by_count":247},{"id":"1402.0590","title":"A Survey of Multi-Objective Sequential Decision-Making","created":"2014-02-04","cited_by_count":242},{"id":"2410.20092","title":"OGBench: Benchmarking Offline Goal-Conditioned RL","created":"2024-10-26","cited_by_count":238},{"id":"1611.04201","title":"CAD2RL: Real Single-Image Flight without a Single Real Image","created":"2016-11-13","cited_by_count":233},{"id":"1707.04175","title":"Distral: Robust Multitask Reinforcement Learning","created":"2017-07-13","cited_by_count":233},{"id":"1511.06342","title":"Actor-Mimic: Deep Multitask and Transfer Reinforcement Learning","created":"2015-11-19","cited_by_count":178},{"id":"1908.08342","title":"A Generalized Algorithm for Multi-Objective Reinforcement Learning and Policy Adaptation","created":"2019-08-21","cited_by_count":177},{"id":"2006.05990","title":"What Matters In On-Policy Reinforcement Learning? A Large-Scale Empirical Study","created":"2020-06-10","cited_by_count":162},{"id":"2403.03950","title":"Stop Regressing: Training Value Functions via Classification for Scalable Deep RL","created":"2024-03-06","cited_by_count":144},{"id":"1809.04474","title":"Multi-task Deep Reinforcement Learning with PopArt","created":"2018-09-12","cited_by_count":141},{"id":"1912.02875","title":"Reinforcement Learning Upside Down: Don't Predict Rewards -- Just Map Them to Actions","created":"2019-12-05","cited_by_count":125},{"id":"2103.07945","title":"Learning One Representation to Optimize All Rewards","created":"2021-03-14","cited_by_count":115},{"id":"2110.02034","title":"Dropout Q-Functions for Doubly Efficient Reinforcement Learning","created":"2021-10-05","cited_by_count":114},{"id":"2403.10506","title":"HumanoidBench: Simulated Humanoid Benchmark for Whole-Body Locomotion and Manipulation","created":"2024-03-15","cited_by_count":112},{"id":"2405.16158","title":"Bigger, Regularized, Optimistic: scaling for compute and sample-efficient continuous control","created":"2024-05-25","cited_by_count":108},{"id":"1812.07626","title":"Universal Successor Features Approximators","created":"2018-12-18","cited_by_count":103},{"id":"1912.13465","title":"Reward-Conditioned Policies","created":"2019-12-31","cited_by_count":102},{"id":"1809.07803","title":"Dynamic Weights in Multi-Objective Deep Reinforcement Learning","created":"2018-09-20","cited_by_count":100},{"id":"1611.08219","title":"The Off-Switch Game","created":"2016-11-24","cited_by_count":97},{"id":"1901.10964","title":"Transfer in Deep Reinforcement Learning Using Successor Features and Generalised Policy Improvement","created":"2019-01-30","cited_by_count":88},{"id":"2209.14935","title":"Does Zero-Shot Reinforcement Learning Exist?","created":"2022-09-29","cited_by_count":83},{"id":"2110.03239","title":"Understanding Domain Randomization for Sim-to-real Transfer","created":"2021-10-07","cited_by_count":80},{"id":"2211.15144","title":"Offline Q-Learning on Diverse Multi-Task Data Both Scales And Generalizes","created":"2022-11-28","cited_by_count":73},{"id":"2006.12862","title":"Automatic Data Augmentation for Generalization in Deep Reinforcement Learning","created":"2020-06-23","cited_by_count":71},{"id":"2410.01131","title":"nGPT: Normalized Transformer with Representation Learning on the Hypersphere","created":"2024-10-01","cited_by_count":70},{"id":"2502.03349","title":"Robust Autonomy Emerges from Self-Play","created":"2025-02-05","cited_by_count":67},{"id":"2412.07762","title":"Efficient Online Reinforcement Learning Fine-Tuning Need Not Retain Offline Data","created":"2024-12-10","cited_by_count":63},{"id":"2506.04168","title":"Horizon Reduction Makes RL Scalable","created":"2025-06-04","cited_by_count":57},{"id":"2504.11054","title":"Zero-Shot Whole-Body Humanoid Control via Behavioral Foundation Models","created":"2025-04-15","cited_by_count":56},{"id":"2301.07784","title":"Sample-Efficient Multi-Objective Learning via Generalized Policy Improvement Prioritization","created":"2023-01-18","cited_by_count":48},{"id":"2505.22642","title":"FastTD3: Simple, Fast, and Capable Reinforcement Learning for Humanoid Control","created":"2025-05-28","cited_by_count":44},{"id":"2501.16142","title":"Towards General-Purpose Model-Free Reinforcement Learning","created":"2025-01-27","cited_by_count":41},{"id":"2502.15280","title":"Hyperspherical Normalization for Scalable Deep Reinforcement Learning","created":"2025-02-21","cited_by_count":38},{"id":"2211.15055","title":"AdaTask: A Task-aware Adaptive Learning Rate Approach to Multi-task Learning","created":"2022-11-28","cited_by_count":31},{"id":"2402.17135","title":"Unsupervised Zero-Shot Reinforcement Learning via Functional Reward Encodings","created":"2024-02-27","cited_by_count":31},{"id":"2505.23150","title":"Bigger, Regularized, Categorical: High-Capacity Value Functions are Efficient Multi-Task Learners","created":"2025-05-29","cited_by_count":23},{"id":"2206.11326","title":"Optimistic Linear Support and Successor Features as a Basis for Optimal Policy Transfer","created":"2022-06-22","cited_by_count":22},{"id":"2504.07896","title":"Fast Adaptation with Behavioral Foundation Models","created":"2025-04-10","cited_by_count":21},{"id":"2401.17173","title":"Zero-Shot Reinforcement Learning via Function Encoders","created":"2024-01-30","cited_by_count":18},{"id":"2509.25174","title":"XQC: Well-conditioned Optimization Accelerates Deep Reinforcement Learning","created":"2025-09-29","cited_by_count":17},{"id":"2410.08896","title":"MAD-TD: Model-Augmented Data stabilizes High Update Ratio RL","created":"2024-10-11","cited_by_count":16},{"id":"2310.15940","title":"Combining Behaviors with the Successor Features Keyboard","created":"2023-10-24","cited_by_count":12},{"id":"2408.14785","title":"Unsupervised-to-Online Reinforcement Learning","created":"2024-08-27","cited_by_count":11},{"id":"2410.22133","title":"Learning Successor Features the Simple Way","created":"2024-10-29","cited_by_count":10},{"id":"2510.21995","title":"Is Temporal Difference Learning the Gold Standard for Stitching in RL?","created":"2025-10-24","cited_by_count":4}],"next_cursor":null}