{"total":177,"rows":[{"id":"2108.11887","title":"Federated Reinforcement Learning: Techniques, Applications, and Open Challenges","created":"2021-08-26","cited_by_count":81,"area":null},{"id":"2103.04000","title":"Off-Belief Learning","created":"2021-03-06","cited_by_count":75,"area":null},{"id":"2306.00577","title":"TorchRL: A data-driven decision-making library for PyTorch","created":"2023-06-01","cited_by_count":60,"area":null},{"id":"2109.06668","title":"Exploration in Deep Reinforcement Learning: From Single-Agent to Multiagent Domain","created":"2021-09-14","cited_by_count":58,"area":null},{"id":"2312.12044","title":"XLand-MiniGrid: Scalable Meta-Reinforcement Learning Environments in JAX","created":"2023-12-19","cited_by_count":55,"area":null},{"id":"2111.11032","title":"Episodic Multi-agent Reinforcement Learning with Curiosity-Driven Exploration","created":"2021-11-22","cited_by_count":49,"area":null},{"id":"2210.02019","title":"Atari-5: Distilling the Arcade Learning Environment down to Five Games","created":"2022-10-05","cited_by_count":44,"area":null},{"id":"2109.08267","title":"CompilerGym: Robust, Performant Compiler Optimization Environments for AI Research","created":"2021-09-17","cited_by_count":41,"area":null},{"id":"2102.07920","title":"Training Larger Networks for Deep Reinforcement Learning","created":"2021-02-16","cited_by_count":38,"area":null},{"id":"2104.06272","title":"Podracer architectures for scalable Reinforcement Learning","created":"2021-04-13","cited_by_count":38,"area":null},{"id":"2510.12633","title":"Laminar: A Scalable Asynchronous RL Post-Training Framework","created":"2025-10-14","cited_by_count":37,"area":null},{"id":"2105.01099","title":"Reinforcement Learning for Ridesharing: An Extended Survey","created":"2021-05-03","cited_by_count":35,"area":null},{"id":"2106.11365","title":"Distributed Heuristic Multi-Agent Path Finding with Communication","created":"2021-06-21","cited_by_count":32,"area":null},{"id":"2207.07166","title":"K-level Reasoning for Zero-Shot Coordination in Hanabi","created":"2022-07-14","cited_by_count":32,"area":null},{"id":"2306.05483","title":"On the Importance of Exploration for Generalization in Reinforcement Learning","created":"2023-06-08","cited_by_count":31,"area":null},{"id":"2103.11512","title":"Robust Multi-Modal Policies for Industrial Assembly via Reinforcement Learning and Demonstrations: A Large-Scale Study","created":"2021-03-21","cited_by_count":30,"area":null},{"id":"2110.01411","title":"Deep Reinforcement Learning Versus Evolution Strategies: A Comparative Survey","created":"2021-09-28","cited_by_count":28,"area":null},{"id":"2202.06626","title":"MuZero with Self-competition for Rate Control in VP9 Video Compression","created":"2022-02-14","cited_by_count":28,"area":null},{"id":"2209.07550","title":"Human-level Atari 200x faster","created":"2022-09-15","cited_by_count":28,"area":null},{"id":"2209.08483","title":"Honor of Kings Arena: an Environment for Generalization in Competitive Reinforcement Learning","created":"2022-09-18","cited_by_count":28,"area":null},{"id":"2102.04736","title":"Reverb: A Framework For Experience Replay","created":"2021-02-09","cited_by_count":27,"area":null},{"id":"2102.12425","title":"Synthetic Returns for Long-Term Credit Assignment","created":"2021-02-24","cited_by_count":27,"area":null},{"id":"2106.02097","title":"A Consciousness-Inspired Planning Agent for Model-Based Reinforcement Learning","created":"2021-06-03","cited_by_count":27,"area":null},{"id":"2209.07364","title":"Continuous MDP Homomorphisms and Homomorphic Policy Gradient","created":"2022-09-15","cited_by_count":27,"area":null},{"id":"2103.04972","title":"Provably Efficient Cooperative Multi-Agent Reinforcement Learning with Function Approximation","created":"2021-03-08","cited_by_count":23,"area":null},{"id":"2205.02388","title":"Interactive Grounded Language Understanding in a Collaborative Environment: IGLU 2021","created":"2022-05-05","cited_by_count":23,"area":null},{"id":"2211.15557","title":"Beyond CAGE: Investigating Generalization of Learned Autonomous Network Defense Policies","created":"2022-11-28","cited_by_count":23,"area":null},{"id":"2102.13515","title":"Beyond Fine-Tuning: Transferring Behavior in Reinforcement Learning","created":"2021-02-24","cited_by_count":21,"area":null},{"id":"2106.03050","title":"Efficient Continuous Control with Double Actors and Regularized Critics","created":"2021-06-06","cited_by_count":21,"area":null},{"id":"2106.15200","title":"Action Set Based Policy Optimization for Safe Power Grid Management","created":"2021-06-29","cited_by_count":21,"area":null},{"id":"2108.11811","title":"When should agents explore?","created":"2021-08-26","cited_by_count":20,"area":null},{"id":"2209.00532","title":"Actor Prioritized Experience Replay","created":"2022-09-01","cited_by_count":20,"area":null},{"id":"2302.10418","title":"MAC-PO: Multi-Agent Experience Replay via Collective Priority Optimization","created":"2023-02-21","cited_by_count":20,"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":"2103.07013","title":"Large Batch Simulation for Deep Reinforcement Learning","created":"2021-03-12","cited_by_count":19,"area":null},{"id":"2109.15316","title":"Scalable Online Planning via Reinforcement Learning Fine-Tuning","created":"2021-09-30","cited_by_count":18,"area":null},{"id":"2306.15934","title":"Curious Replay for Model-based Adaptation","created":"2023-06-28","cited_by_count":16,"area":null},{"id":"2504.14588","title":"Phoenix: A Motion-based Self-Reflection Framework for Fine-grained Robotic Action Correction","created":"2025-04-20","cited_by_count":16,"area":null},{"id":"2111.06978","title":"RLOps: Development Life-cycle of Reinforcement Learning Aided Open RAN","created":"2021-11-12","cited_by_count":15,"area":null},{"id":"2101.08153","title":"Shielding Atari Games with Bounded Prescience","created":"2021-01-20","cited_by_count":14,"area":null},{"id":"2110.01528","title":"Large Batch Experience Replay","created":"2021-10-04","cited_by_count":14,"area":null},{"id":"2202.05195","title":"Uncovering Instabilities in Variational-Quantum Deep Q-Networks","created":"2022-02-10","cited_by_count":14,"area":null},{"id":"2106.15860","title":"Understanding Adversarial Attacks on Observations in Deep Reinforcement Learning","created":"2021-06-30","cited_by_count":13,"area":null},{"id":"2206.00165","title":"Byzantine-Robust Online and Offline Distributed Reinforcement Learning","created":"2022-06-01","cited_by_count":13,"area":null},{"id":"2112.04145","title":"A Review for Deep Reinforcement Learning in Atari:Benchmarks, Challenges, and Solutions","created":"2021-12-08","cited_by_count":12,"area":null},{"id":"2212.02094","title":"Learning Physically Realizable Skills for Online Packing of General 3D Shapes","created":"2022-12-05","cited_by_count":12,"area":null},{"id":"2102.10740","title":"Communication Efficient Parallel Reinforcement Learning","created":"2021-02-22","cited_by_count":10,"area":null},{"id":"2103.16511","title":"Flatland Competition 2020: MAPF and MARL for Efficient Train Coordination on a Grid World","created":"2021-03-30","cited_by_count":10,"area":null},{"id":"2111.05992","title":"On the Use and Misuse of Absorbing States in Multi-agent Reinforcement Learning","created":"2021-11-10","cited_by_count":10,"area":null},{"id":"2111.10247","title":"Fast and Data-Efficient Training of Rainbow: an Experimental Study on Atari","created":"2021-11-19","cited_by_count":10,"area":null},{"id":"2206.05060","title":"Social Network Structure Shapes Innovation: Experience-sharing in RL with SAPIENS","created":"2022-06-10","cited_by_count":10,"area":null},{"id":"2306.16688","title":"SRL: Scaling Distributed Reinforcement Learning to Over Ten Thousand Cores","created":"2023-06-29","cited_by_count":10,"area":null},{"id":"2308.10284","title":"Towards Few-shot Coordination: Revisiting Ad-hoc Teamplay Challenge In the Game of Hanabi","created":"2023-08-20","cited_by_count":10,"area":null},{"id":"2112.03798","title":"PTR-PPO: Proximal Policy Optimization with Prioritized Trajectory Replay","created":"2021-12-07","cited_by_count":9,"area":null},{"id":"2206.12848","title":"Analysis of Stochastic Processes through Replay Buffers","created":"2022-06-26","cited_by_count":9,"area":null},{"id":"2305.06446","title":"Cooperative Multi-Agent Reinforcement Learning: Asynchronous Communication and Linear Function Approximation","created":"2023-05-10","cited_by_count":9,"area":null},{"id":"2509.03682","title":"A Comprehensive Review of Multi-Agent Reinforcement Learning in Video Games","created":"2025-09-03","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":"2105.00990","title":"Hierarchical Reinforcement Learning for Air Combat at DARPA's AlphaDogfight Trials","created":"2021-05-03","cited_by_count":8,"area":null},{"id":"2109.11767","title":"Improved Soft Actor-Critic: Mixing Prioritized Off-Policy Samples with On-Policy Experience","created":"2021-09-24","cited_by_count":8,"area":null},{"id":"2207.14561","title":"Cyclic Policy Distillation: Sample-Efficient Sim-to-Real Reinforcement Learning with Domain Randomization","created":"2022-07-29","cited_by_count":8,"area":null},{"id":"2212.04401","title":"A Rubric for Human-like Agents and NeuroAI","created":"2022-12-08","cited_by_count":8,"area":null},{"id":"2101.09650","title":"GST: Group-Sparse Training for Accelerating Deep Reinforcement Learning","created":"2021-01-24","cited_by_count":7,"area":null},{"id":"2102.03261","title":"Revisiting Prioritized Experience Replay: A Value Perspective","created":"2021-02-05","cited_by_count":7,"area":null},{"id":"2110.00445","title":"Sim and Real: Better Together","created":"2021-10-01","cited_by_count":7,"area":null},{"id":"2201.00006","title":"Leveraging Queue Length and Attention Mechanisms for Enhanced Traffic Signal Control Optimization","created":"2021-12-30","cited_by_count":7,"area":null},{"id":"2206.08888","title":"Fast Population-Based Reinforcement Learning on a Single Machine","created":"2022-06-17","cited_by_count":7,"area":null},{"id":"2310.00036","title":"Cleanba: A Reproducible and Efficient Distributed Reinforcement Learning Platform","created":"2023-09-29","cited_by_count":7,"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":"2104.10262","title":"Network Defense is Not a Game","created":"2021-04-20","cited_by_count":6,"area":null},{"id":"2111.12340","title":"How does AI play football? An analysis of RL and real-world football strategies","created":"2021-11-24","cited_by_count":6,"area":null},{"id":"2112.11216","title":"Value Activation for Bias Alleviation: Generalized-activated Deep Double Deterministic Policy Gradients","created":"2021-12-21","cited_by_count":6,"area":null},{"id":"2206.10122","title":"Safe and Psychologically Pleasant Traffic Signal Control with Reinforcement Learning using Action Masking","created":"2022-06-21","cited_by_count":6,"area":null},{"id":"2208.12328","title":"Autonomous Unmanned Aerial Vehicle Navigation using Reinforcement Learning: A Systematic Review","created":"2022-08-25","cited_by_count":6,"area":null},{"id":"2301.11135","title":"FedHQL: Federated Heterogeneous Q-Learning","created":"2023-01-26","cited_by_count":6,"area":null},{"id":"2309.12038","title":"Uncertainty-driven Exploration Strategies for Online Grasp Learning","created":"2023-09-21","cited_by_count":6,"area":null},{"id":"2502.10177","title":"STMA: A Spatio-Temporal Memory Agent for Long-Horizon Embodied Task Planning","created":"2025-02-14","cited_by_count":6,"area":null},{"id":"2108.06898","title":"Neural-to-Tree Policy Distillation with Policy Improvement Criterion","created":"2021-08-16","cited_by_count":5,"area":null},{"id":"2109.14727","title":"Dr Jekyll and Mr Hyde: the Strange Case of Off-Policy Policy Updates","created":"2021-09-29","cited_by_count":5,"area":null},{"id":"2110.13450","title":"Distributed Multi-Agent Deep Reinforcement Learning Framework for Whole-building HVAC Control","created":"2021-10-26","cited_by_count":5,"area":null},{"id":"2112.11731","title":"Graph augmented Deep Reinforcement Learning in the GameRLand3D environment","created":"2021-12-22","cited_by_count":5,"area":null},{"id":"2210.03325","title":"Elastic Step DQN: A novel multi-step algorithm to alleviate overestimation in Deep QNetworks","created":"2022-10-07","cited_by_count":5,"area":null},{"id":"2211.12956","title":"Reinforcement learning for traffic signal control in hybrid action space","created":"2022-11-23","cited_by_count":5,"area":null},{"id":"2306.07552","title":"Galactic: Scaling End-to-End Reinforcement Learning for Rearrangement at 100k Steps-Per-Second","created":"2023-06-13","cited_by_count":5,"area":null},{"id":"2306.16133","title":"Training Deep Surrogate Models with Large Scale Online Learning","created":"2023-06-28","cited_by_count":5,"area":null},{"id":"2308.15039","title":"R^3: On-device Real-Time Deep Reinforcement Learning for Autonomous Robotics","created":"2023-08-29","cited_by_count":5,"area":null},{"id":"2312.08365","title":"An Invitation to Deep Reinforcement Learning","created":"2023-12-13","cited_by_count":5,"area":null},{"id":"2603.01501","title":"GAC: Stabilizing Asynchronous RL Training for LLMs via Gradient Alignment Control","created":"2026-03-02","cited_by_count":5,"area":null},{"id":"2112.03636","title":"Godot Reinforcement Learning Agents","created":"2021-12-07","cited_by_count":4,"area":null},{"id":"2210.12448","title":"Probing Transfer in Deep Reinforcement Learning without Task Engineering","created":"2022-10-22","cited_by_count":4,"area":null},{"id":"2212.00253","title":"Distributed Deep Reinforcement Learning: A Survey and A Multi-Player Multi-Agent Learning Toolbox","created":"2022-12-01","cited_by_count":4,"area":null},{"id":"2309.15484","title":"Towards Human-Like RL: Taming Non-Naturalistic Behavior in Deep RL via Adaptive Behavioral Costs in 3D Games","created":"2023-09-27","cited_by_count":4,"area":null},{"id":"2102.12307","title":"Balancing Rational and Other-Regarding Preferences in Cooperative-Competitive Environments","created":"2021-02-24","cited_by_count":3,"area":null},{"id":"2102.13565","title":"Low-Precision Reinforcement Learning: Running Soft Actor-Critic in Half Precision","created":"2021-02-26","cited_by_count":3,"area":null},{"id":"2105.10211","title":"Multi-Agent Deep Reinforcement Learning using Attentive Graph Neural Architectures for Real-Time Strategy Games","created":"2021-05-21","cited_by_count":3,"area":null},{"id":"2111.08819","title":"CleanRL: High-quality Single-file Implementations of Deep Reinforcement Learning Algorithms","created":"2021-11-16","cited_by_count":3,"area":null},{"id":"2204.10374","title":"Learning how to Interact with a Complex Interface using Hierarchical Reinforcement Learning","created":"2022-04-21","cited_by_count":3,"area":null},{"id":"2301.08688","title":"Asynchronous Deep Double Duelling Q-Learning for Trading-Signal Execution in Limit Order Book Markets","created":"2023-01-20","cited_by_count":3,"area":null},{"id":"2303.12992","title":"A Survey of Historical Learning: Learning Models with Learning History","created":"2023-03-23","cited_by_count":3,"area":null},{"id":"2305.04180","title":"Train a Real-world Local Path Planner in One Hour via Partially Decoupled Reinforcement Learning and Vectorized Diversity","created":"2023-05-07","cited_by_count":3,"area":null}],"next_cursor":"100"}