{"total":85,"rows":[{"id":"2205.12548","title":"RLPrompt: Optimizing Discrete Text Prompts with Reinforcement Learning","created":"2022-05-25","cited_by_count":366,"area":null},{"id":"2107.12808","title":"Open-Ended Learning Leads to Generally Capable Agents","created":"2021-07-27","cited_by_count":182,"area":null},{"id":"2103.04551","title":"Behavior From the Void: Unsupervised Active Pre-Training","created":"2021-03-08","cited_by_count":174,"area":null},{"id":"2107.14171","title":"Tianshou: a Highly Modularized Deep Reinforcement Learning Library","created":"2021-07-29","cited_by_count":143,"area":null},{"id":"2107.00644","title":"Stabilizing Deep Q-Learning with ConvNets and Vision Transformers under Data Augmentation","created":"2021-07-01","cited_by_count":105,"area":null},{"id":"2402.18762","title":"Disentangling the Causes of Plasticity Loss in Neural Networks","created":"2024-02-29","cited_by_count":86,"area":"deeprl"},{"id":"2201.04122","title":"In Defense of the Unitary Scalarization for Deep Multi-Task Learning","created":"2022-01-11","cited_by_count":67,"area":null},{"id":"2104.06159","title":"Muesli: Combining Improvements in Policy Optimization","created":"2021-04-13","cited_by_count":53,"area":null},{"id":"2305.14106","title":"Better Zero-Shot Reasoning with Self-Adaptive Prompting","created":"2023-05-23","cited_by_count":52,"area":"lr"},{"id":"2412.08442","title":"From Multimodal LLMs to Generalist Embodied Agents: Methods and Lessons","created":"2024-12-11","cited_by_count":42,"area":"mllm"},{"id":"2310.09971","title":"AMAGO: Scalable In-Context Reinforcement Learning for Adaptive Agents","created":"2023-10-15","cited_by_count":41,"area":null},{"id":"1809.02064","title":"Sample-Efficient Imitation Learning via Generative Adversarial Nets","created":"2018-09-06","cited_by_count":36,"area":"offlinerl"},{"id":"2305.03286","title":"Composite Motion Learning with Task Control","created":"2023-05-05","cited_by_count":28,"area":null},{"id":"2410.14606","title":"Streaming Deep Reinforcement Learning Finally Works","created":"2024-10-18","cited_by_count":25,"area":"deeprl"},{"id":"2105.05347","title":"Return-based Scaling: Yet Another Normalisation Trick for Deep RL","created":"2021-05-11","cited_by_count":23,"area":null},{"id":"2509.22047","title":"MO-GRPO: Mitigating Reward Hacking of Group Relative Policy Optimization on Multi-Objective Problems","created":"2025-09-26","cited_by_count":23,"area":"lr"},{"id":"2107.05431","title":"CoBERL: Contrastive BERT for Reinforcement Learning","created":"2021-07-12","cited_by_count":21,"area":null},{"id":"2310.08348","title":"LightZero: A Unified Benchmark for Monte Carlo Tree Search in General Sequential Decision Scenarios","created":"2023-10-12","cited_by_count":20,"area":null},{"id":"2405.19988","title":"Video-Language Critic: Transferable Reward Functions for Language-Conditioned Robotics","created":"2024-05-30","cited_by_count":19,"area":"alignment"},{"id":"2205.14205","title":"ALMA: Hierarchical Learning for Composite Multi-Agent Tasks","created":"2022-05-27","cited_by_count":18,"area":null},{"id":"2405.09999","title":"Reward Centering","created":"2024-05-16","cited_by_count":16,"area":"deeprl"},{"id":"2006.16785","title":"Lipschitzness Is All You Need To Tame Off-policy Generative Adversarial Imitation Learning","created":"2020-06-28","cited_by_count":15,"area":"offlinerl"},{"id":"2412.07165","title":"A Method for Evaluating Hyperparameter Sensitivity in Reinforcement Learning","created":"2024-12-10","cited_by_count":15,"area":"deeprl"},{"id":"2103.10369","title":"Combining Pessimism with Optimism for Robust and Efficient Model-Based Deep Reinforcement Learning","created":"2021-03-18","cited_by_count":14,"area":null},{"id":"2204.00656","title":"Consistency driven Sequential Transformers Attention Model for Partially Observable Scenes","created":"2022-04-01","cited_by_count":11,"area":null},{"id":"2408.10932","title":"The Evolution of Reinforcement Learning in Quantitative Finance: A Survey","created":"2024-08-20","cited_by_count":11,"area":"deeprl"},{"id":"2402.06819","title":"Monitored Markov Decision Processes","created":"2024-02-09","cited_by_count":10,"area":"deeprl"},{"id":"2509.11481","title":"RAPTOR: A Foundation Policy for Quadrotor Control","created":"2025-09-15","cited_by_count":8,"area":null},{"id":"2310.17805","title":"Reward Scale Robustness for Proximal Policy Optimization via DreamerV3 Tricks","created":"2023-10-26","cited_by_count":7,"area":null},{"id":"2311.11557","title":"Replay-enhanced Continual Reinforcement Learning","created":"2023-11-20","cited_by_count":7,"area":null},{"id":"2202.11664","title":"Comparative analysis of machine learning methods for active flow control","created":"2022-02-23","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":"2302.02182","title":"Online Reinforcement Learning in Non-Stationary Context-Driven Environments","created":"2023-02-04","cited_by_count":6,"area":null},{"id":"2509.22442","title":"Learning to Ball: Composing Policies for Long-Horizon Basketball Moves","created":"2025-09-26","cited_by_count":6,"area":"deeprl"},{"id":"2110.04698","title":"A Closer Look at Advantage-Filtered Behavioral Cloning in High-Noise Datasets","created":"2021-10-10","cited_by_count":5,"area":"offlinerl"},{"id":"2502.20265","title":"On the Importance of Reward Design in Reinforcement Learning-based Dynamic Algorithm Configuration: A Case Study on OneMax with (1+($\\lambda$,$\\lambda$))-GA","created":"2025-02-27","cited_by_count":5,"area":"deeprl"},{"id":"2311.15594","title":"Networked Multiagent Safe Reinforcement Learning for Low-carbon Demand Management in Distribution Network","created":"2023-11-27","cited_by_count":4,"area":null},{"id":"2407.18143","title":"Maximum Entropy On-Policy Actor-Critic via Entropy Advantage Estimation","created":"2024-07-25","cited_by_count":4,"area":"deeprl"},{"id":"2101.05372","title":"A Deep Reinforcement Learning Framework for Eco-driving in Connected and Automated Hybrid Electric Vehicles","created":"2021-01-13","cited_by_count":3,"area":"driving"},{"id":"2102.09361","title":"Efficient Reinforcement Learning in Resource Allocation Problems Through Permutation Invariant Multi-task Learning","created":"2021-02-18","cited_by_count":3,"area":null},{"id":"2104.12895","title":"Computational Performance of Deep Reinforcement Learning to find Nash Equilibria","created":"2021-04-26","cited_by_count":3,"area":null},{"id":"2104.14138","title":"Adapting to Reward Progressivity via Spectral Reinforcement Learning","created":"2021-04-29","cited_by_count":3,"area":null},{"id":"2112.01765","title":"Learning Emergent Random Access Protocol for LEO Satellite Networks","created":"2021-12-03","cited_by_count":3,"area":null},{"id":"2207.07790","title":"BCRLSP: An Offline Reinforcement Learning Framework for Sequential Targeted Promotion","created":"2022-07-16","cited_by_count":3,"area":"offlinerl"},{"id":"2306.04403","title":"Policy-Based Self-Competition for Planning Problems","created":"2023-06-07","cited_by_count":3,"area":null},{"id":"2505.03181","title":"VLM Q-Learning: Aligning Vision-Language Models for Interactive Decision-Making","created":"2025-05-06","cited_by_count":3,"area":"lr"},{"id":"2601.05002","title":"On the Hidden Objective Biases of Group-based Reinforcement Learning","created":"2026-01-08","cited_by_count":3,"area":"lr"},{"id":"2101.02663","title":"L2PF -- Learning to Prune Faster","created":"2021-01-07","cited_by_count":2,"area":null},{"id":"2201.05560","title":"Demystifying Reinforcement Learning in Time-Varying Systems","created":"2022-01-14","cited_by_count":2,"area":null},{"id":"2209.09329","title":"MAN: Multi-Action Networks Learning","created":"2022-09-19","cited_by_count":2,"area":null},{"id":"2305.18269","title":"Doing the right thing for the right reason: Evaluating artificial moral cognition by probing cost insensitivity","created":"2023-05-29","cited_by_count":2,"area":null},{"id":"2406.10242","title":"Physics-Guided Actor-Critic Reinforcement Learning for Swimming in Turbulence","created":"2024-06-05","cited_by_count":2,"area":"deeprl"},{"id":"2602.06746","title":"Semantically Labelled Automata for Multi-Task Reinforcement Learning with LTL Instructions","created":"2026-02-06","cited_by_count":2,"area":"deeprl"},{"id":"2406.01838","title":"Learning the Target Network in Function Space","created":"2024-06-03","cited_by_count":1,"area":"deeprl"},{"id":"2510.00922","title":"On Discovering Algorithms for Adversarial Imitation Learning","created":"2025-10-01","cited_by_count":1,"area":"offlinerl"},{"id":"2511.08174","title":"Deep (Predictive) Discounted Counterfactual Regret Minimization","created":"2025-11-11","cited_by_count":1,"area":null},{"id":"2512.03805","title":"Deep Reinforcement Learning for Dynamic Algorithm Configuration: A Case Study on Optimizing OneMax with the (1+($\\lambda$,$\\lambda$))-GA","created":"2025-12-03","cited_by_count":1,"area":"deeprl"},{"id":"2603.11395","title":"ARROW: Augmented Replay for RObust World models","created":"2026-03-12","cited_by_count":1,"area":"wm"},{"id":"2607.13028","title":"TerraZero: Procedural Driving Simulation for Zero-Demonstration Self-Play at Scale","created":"2026-07-14","cited_by_count":1,"area":"driving"},{"id":"2607.16534","title":"Building2Building: A Large Scale Benchmark for Generalizable Real-World Reinforcement Learning","created":"2026-07-17","cited_by_count":1,"area":"deeprl"},{"id":"2101.01178","title":"Advances in Electron Microscopy with Deep Learning","created":"2021-01-04","cited_by_count":0,"area":null},{"id":"2306.00975","title":"Active Vision Reinforcement Learning under Limited Visual Observability","created":"2023-06-01","cited_by_count":0,"area":null},{"id":"2308.12649","title":"APART: Diverse Skill Discovery using All Pairs with Ascending Reward and DropouT","created":"2023-08-24","cited_by_count":0,"area":null},{"id":"2310.06415","title":"Deep reinforcement learning uncovers processes for separating azeotropic mixtures without prior knowledge","created":"2023-10-10","cited_by_count":0,"area":null},{"id":"2505.07832","title":"A General Approach of Automated Environment Design for Learning the Optimal Power Flow","created":"2025-05-01","cited_by_count":0,"area":"deeprl"},{"id":"2603.19864","title":"NASimJax: A GPU-Accelerated Policy Learning Framework for Penetration Testing","created":"2026-03-20","cited_by_count":0,"area":null},{"id":"2603.29272","title":"MaskAdapt: Learning Flexible Motion Adaptation via Mask-Invariant Prior for Physics-Based Characters","created":"2026-03-31","cited_by_count":0,"area":null},{"id":"2604.26150","title":"Reinforcement Learning for Public Safety Power Shutoffs Under Decision-Dependent Uncertainty and Nonlinear Wildfire Ignition Models","created":"2026-04-28","cited_by_count":0,"area":"deeprl"},{"id":"2605.04368","title":"Extending Differential Temporal Difference Methods for Episodic Problems","created":"2026-05-06","cited_by_count":0,"area":"deeprl"},{"id":"2605.11473","title":"TOPPO: Rethinking PPO for Multi-Task Reinforcement Learning with Critic Balancing","created":"2026-05-12","cited_by_count":0,"area":"deeprl"},{"id":"2606.19633","title":"CTS-MoE: Implicit Terrain Adaptation via Mixture-of-Experts for Perceptive Locomotion","created":"2026-06-17","cited_by_count":0,"area":"moe"},{"id":"2606.29806","title":"Accelerating Q-learning through Efficient Value-Sharing across Actions","created":"2026-06-29","cited_by_count":0,"area":"deeprl"},{"id":"2607.01880","title":"Learning the Supports for Categorical Critic in Reinforcement Learning","created":"2026-07-02","cited_by_count":0,"area":"deeprl"},{"id":"2607.22644","title":"DocHRL: A Hierarchical Reinforcement Learning Framework for Cost-Optimised Document Classification","created":"2026-06-24","cited_by_count":0,"area":"lr"},{"id":"2608.04305","title":"Adaptive Finite-Budget Training for CVaR Risk-Aware Q-Learning","created":"2026-08-05","cited_by_count":0,"area":"deeprl"},{"id":"2608.12256","title":"SelectLight: Learning to Select Signal Plans Generated by Distributed Model Predictive Control for Urban Traffic Networks","created":"2026-08-12","cited_by_count":0,"area":"deeprl"},{"id":"2608.26481","title":"Shared Actors Need Not Share Critics: Effects of Value Mismatch in Parallel Reinforcement Learning","created":"2026-08-27","cited_by_count":0,"area":"deeprl"},{"id":"2609.34695","title":"Sufficiency of Zeroth-Order Reward Shaping for Policy Gradient in Stabilization Control","created":"2026-09-28","cited_by_count":0,"area":"deeprl"},{"id":"2609.35347","title":"Beyond Teacher Assignment: Domain-Normalized Multi-Teacher On-Policy Distillation","created":"2026-09-28","cited_by_count":0,"area":"lr"},{"id":"2609.36802","title":"EasyPPO: Stabilizing the Critic Is Key","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.39757","title":"Revisiting On-policy Adversarial Black-Box Distillation: Calibrating Groupwise Reward Geometry for Effective Advantage Construction","created":"2026-09-30","cited_by_count":0,"area":"distill"},{"id":"2610.02074","title":"Homomorphic Advantage Operator: Stabilizing Reinforcement Learning Under Fully Homomorphic Encryption Constraints","created":"2026-10-01","cited_by_count":0,"area":"deeprl"},{"id":"2610.02545","title":"Reward Inflation: A Healthy Stimulus for Reinforcement Learning","created":"2026-10-01","cited_by_count":0,"area":"deeprl"},{"id":"2610.06833","title":"Towards Looped Models Done Right, Part II: Rethinking at Fixed Points","created":"2026-10-05","cited_by_count":0,"area":"lr"},{"id":"2610.18186","title":"Reinforcement Learning for Large-Scale Lifelong Multi-Agent Path Finding with Shared Spatial Fields","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}