{"total":269,"rows":[{"id":"2306.16927","title":"End-to-end Autonomous Driving: Challenges and Frontiers","created":"2023-06-29","cited_by_count":490,"area":"driving"},{"id":"1811.07871","title":"Scalable agent alignment via reward modeling: a research direction","created":"2018-11-19","cited_by_count":447,"area":"alignment"},{"id":"2108.11887","title":"Federated Reinforcement Learning: Techniques, Applications, and Open Challenges","created":"2021-08-26","cited_by_count":81,"area":null},{"id":"2407.04811","title":"Simplifying Deep Temporal Difference Learning","created":"2024-07-05","cited_by_count":78,"area":"deeprl"},{"id":"2103.04000","title":"Off-Belief Learning","created":"2021-03-06","cited_by_count":75,"area":null},{"id":"2410.14803","title":"DistRL: An Asynchronous Distributed Reinforcement Learning Framework for On-Device Control Agents","created":"2024-10-18","cited_by_count":68,"area":"lr"},{"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":"1910.01077","title":"Task-Relevant Adversarial Imitation Learning","created":"2019-10-02","cited_by_count":45,"area":"offlinerl"},{"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":"1911.00459","title":"Positive-Unlabeled Reward Learning","created":"2019-11-01","cited_by_count":37,"area":"alignment"},{"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":"2109.05413","title":"Learning Selective Communication for Multi-Agent Path Finding","created":"2021-09-12","cited_by_count":32,"area":"offlinerl"},{"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":"2503.18929","title":"Trajectory Balance with Asynchrony: Decoupling Exploration and Learning for Fast, Scalable LLM Post-Training","created":"2025-03-24","cited_by_count":29,"area":"lr"},{"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":"2306.13085","title":"Harnessing Mixed Offline Reinforcement Learning Datasets via Trajectory Weighting","created":"2023-06-22","cited_by_count":22,"area":"offlinerl"},{"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":"2211.11092","title":"Q-Ensemble for Offline RL: Don't Scale the Ensemble, Scale the Batch Size","created":"2022-11-20","cited_by_count":21,"area":"offlinerl"},{"id":"2407.20230","title":"SAPG: Split and Aggregate Policy Gradients","created":"2024-07-29","cited_by_count":21,"area":"deeprl"},{"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":"2406.07876","title":"Small Scale Data-Free Knowledge Distillation","created":"2024-06-12","cited_by_count":20,"area":"distill"},{"id":"2412.12089","title":"Stabilizing Reinforcement Learning in Differentiable Multiphysics Simulation","created":"2024-12-16","cited_by_count":20,"area":"deeprl"},{"id":"2103.07013","title":"Large Batch Simulation for Deep Reinforcement Learning","created":"2021-03-12","cited_by_count":19,"area":null},{"id":"2207.10148","title":"Learning Deformable Object Manipulation from Expert Demonstrations","created":"2022-07-20","cited_by_count":19,"area":"offlinerl"},{"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":"2409.18197","title":"Autonomous Network Defence using Reinforcement Learning","created":"2024-09-26","cited_by_count":15,"area":"deeprl"},{"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":"2006.07442","title":"Self-Imitation Learning via Generalized Lower Bound Q-learning","created":"2020-06-12","cited_by_count":13,"area":"offlinerl"},{"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":"2307.14993","title":"Thinker: Learning to Plan and Act","created":"2023-07-27","cited_by_count":13,"area":"wm"},{"id":"2506.03404","title":"The Impact of On-Policy Parallelized Data Collection on Deep Reinforcement Learning Networks","created":"2025-06-03","cited_by_count":13,"area":"deeprl"},{"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":"2507.23172","title":"Benchmarking Massively Parallelized Multi-Task Reinforcement Learning for Robotics Tasks","created":"2025-07-31","cited_by_count":11,"area":"deeprl"},{"id":"2509.22601","title":"Learn the Ropes, Then Trust the Wins: Self-imitation with Progressive Exploration for Agentic Reinforcement Learning","created":"2025-09-26","cited_by_count":11,"area":"agents"},{"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":"2504.02515","title":"Exploration-Driven Generative Interactive Environments","created":"2025-04-03","cited_by_count":9,"area":"wm"},{"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":"2411.05614","title":"Acceleration for Deep Reinforcement Learning using Parallel and Distributed Computing: A Survey","created":"2024-11-08","cited_by_count":8,"area":"deeprl"},{"id":"2507.18809","title":"Test-time Offline Reinforcement Learning on Goal-related Experience","created":"2025-07-24","cited_by_count":8,"area":"offlinerl"},{"id":"2508.19506","title":"Learning Game-Playing Agents with Generative Code Optimization","created":"2025-08-27","cited_by_count":8,"area":"agents"},{"id":"2607.01531","title":"OPINE-World: Programmatic World Modeling with Ontology-error-Prioritized Interactive Exploration for ARC-AGI-3","created":"2026-07-01","cited_by_count":8,"area":"wm"},{"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":"2312.11935","title":"Parameterized Decision-making with Multi-modal Perception for Autonomous Driving","created":"2023-12-19","cited_by_count":7,"area":"driving"},{"id":"2410.20487","title":"Efficient Diversity-based Experience Replay for Deep Reinforcement Learning","created":"2024-10-27","cited_by_count":7,"area":"deeprl"},{"id":"2411.03820","title":"Beyond The Rainbow: High Performance Deep Reinforcement Learning on a Desktop PC","created":"2024-11-06","cited_by_count":7,"area":"deeprl"},{"id":"2509.22963","title":"Reinforcement Learning with Discrete Diffusion Policies for Combinatorial Action Spaces","created":"2025-09-26","cited_by_count":7,"area":"diffusion"},{"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}],"next_cursor":"100"}