{"total":93,"rows":[{"id":"2106.14405","title":"Habitat 2.0: Training Home Assistants to Rearrange their Habitat","created":"2021-06-28","cited_by_count":511,"area":null},{"id":"2310.00166","title":"Motif: Intrinsic Motivation from Artificial Intelligence Feedback","created":"2023-09-29","cited_by_count":102,"area":null},{"id":"2206.10558","title":"EnvPool: A Highly Parallel Reinforcement Learning Environment Execution Engine","created":"2022-06-21","cited_by_count":62,"area":null},{"id":"2206.09889","title":"Nocturne: a scalable driving benchmark for bringing multi-agent learning one step closer to the real world","created":"2022-06-20","cited_by_count":56,"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":"2504.17838","title":"CaRL: Learning Scalable Planning Policies with Simple Rewards","created":"2025-04-24","cited_by_count":35,"area":"deeprl"},{"id":"2305.12127","title":"DexPBT: Scaling up Dexterous Manipulation for Hand-Arm Systems with Population Based Training","created":"2023-05-20","cited_by_count":29,"area":null},{"id":"2406.12905","title":"PufferLib: Making Reinforcement Learning Libraries and Environments Play Nice","created":"2024-06-11","cited_by_count":24,"area":null},{"id":"2412.08542","title":"MaestroMotif: Skill Design from Artificial Intelligence Feedback","created":"2024-12-11","cited_by_count":24,"area":null},{"id":"2106.07551","title":"MALib: A Parallel Framework for Population-based Multi-agent Reinforcement Learning","created":"2021-06-05","cited_by_count":23,"area":null},{"id":"2402.02868","title":"Fine-tuning Reinforcement Learning Models is Secretly a Forgetting Mitigation Problem","created":"2024-02-05","cited_by_count":23,"area":"deeprl"},{"id":"2402.09844","title":"Jack of All Trades, Master of Some, a Multi-Purpose Transformer Agent","created":"2024-02-15","cited_by_count":21,"area":null},{"id":"2107.08170","title":"Megaverse: Simulating Embodied Agents at One Million Experiences per Second","created":"2021-07-17","cited_by_count":20,"area":null},{"id":"2203.11889","title":"Insights From the NeurIPS 2021 NetHack Challenge","created":"2022-03-22","cited_by_count":20,"area":null},{"id":"2211.07819","title":"General Intelligence Requires Rethinking Exploration","created":"2022-11-15","cited_by_count":20,"area":null},{"id":"2305.13795","title":"Proximal Policy Gradient Arborescence for Quality Diversity Reinforcement Learning","created":"2023-05-23","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":"2106.01151","title":"Towards Deeper Deep Reinforcement Learning with Spectral Normalization","created":"2021-06-02","cited_by_count":19,"area":null},{"id":"2210.05064","title":"VER: Scaling On-Policy RL Leads to the Emergence of Navigation in Embodied Rearrangement","created":"2022-10-11","cited_by_count":18,"area":null},{"id":"2402.03046","title":"Open RL Benchmark: Comprehensive Tracked Experiments for Reinforcement Learning","created":"2024-02-05","cited_by_count":17,"area":"deeprl"},{"id":"2211.00539","title":"Dungeons and Data: A Large-Scale NetHack Dataset","created":"2022-11-01","cited_by_count":16,"area":"offlinerl"},{"id":"2205.13771","title":"IGLU 2022: Interactive Grounded Language Understanding in a Collaborative Environment at NeurIPS 2022","created":"2022-05-27","cited_by_count":14,"area":null},{"id":"2402.03947","title":"Reinforcement Learning for Collision-free Flight Exploiting Deep Collision Encoding","created":"2024-02-06","cited_by_count":13,"area":"deeprl"},{"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":"2007.02701","title":"Scaling Imitation Learning in Minecraft","created":"2020-07-06","cited_by_count":12,"area":"offlinerl"},{"id":"2210.05409","title":"LECO: Learnable Episodic Count for Task-Specific Intrinsic Reward","created":"2022-10-11","cited_by_count":11,"area":null},{"id":"2305.19240","title":"NetHack is Hard to Hack","created":"2023-05-30","cited_by_count":11,"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":"2306.16688","title":"SRL: Scaling Distributed Reinforcement Learning to Over Ten Thousand Cores","created":"2023-06-29","cited_by_count":10,"area":null},{"id":"2310.08549","title":"Cross-Episodic Curriculum for Transformer Agents","created":"2023-10-12","cited_by_count":10,"area":null},{"id":"2410.23022","title":"Online Intrinsic Rewards for Decision Making Agents from Large Language Model Feedback","created":"2024-10-30","cited_by_count":10,"area":"agents"},{"id":"2206.00142","title":"IGLU Gridworld: Simple and Fast Environment for Embodied Dialog Agents","created":"2022-05-31","cited_by_count":9,"area":null},{"id":"2212.12669","title":"On Realization of Intelligent Decision-Making in the Real World: A Foundation Decision Model Perspective","created":"2022-12-24","cited_by_count":8,"area":null},{"id":"2309.13285","title":"Collision Avoidance and Navigation for a Quadrotor Swarm Using End-to-end Deep Reinforcement Learning","created":"2023-09-23","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":"2501.13200","title":"SRMT: Shared Memory for Multi-agent Lifelong Pathfinding","created":"2025-01-22","cited_by_count":8,"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":"2505.15345","title":"Hadamax Encoding: Elevating Performance in Model-Free Atari","created":"2025-05-21","cited_by_count":7,"area":"deeprl"},{"id":"2206.10944","title":"POGEMA: Partially Observable Grid Environment for Multiple Agents","created":"2022-06-22","cited_by_count":6,"area":null},{"id":"2310.15719","title":"AGaLiTe: Approximate Gated Linear Transformers for Online Reinforcement Learning","created":"2023-10-24","cited_by_count":6,"area":null},{"id":"2503.08241","title":"HASARD: A Benchmark for Vision-Based Safe Reinforcement Learning in Embodied Agents","created":"2025-03-11","cited_by_count":6,"area":"deeprl"},{"id":"2505.14443","title":"Semantically-driven Deep Reinforcement Learning for Inspection Path Planning","created":"2025-05-20","cited_by_count":6,"area":"deeprl"},{"id":"2112.11731","title":"Graph augmented Deep Reinforcement Learning in the GameRLand3D environment","created":"2021-12-22","cited_by_count":5,"area":null},{"id":"2306.09537","title":"QuadSwarm: A Modular Multi-Quadrotor Simulator for Deep Reinforcement Learning with Direct Thrust Control","created":"2023-06-15","cited_by_count":5,"area":null},{"id":"2310.05205","title":"GEAR: A GPU-Centric Experience Replay System for Large Reinforcement Learning Models","created":"2023-10-08","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":"2509.00338","title":"Scalable Option Learning in High-Throughput Environments","created":"2025-08-30","cited_by_count":5,"area":"deeprl"},{"id":"2107.02195","title":"Agents that Listen: High-Throughput Reinforcement Learning with Multiple Sensory Systems","created":"2021-07-05","cited_by_count":4,"area":null},{"id":"2112.03636","title":"Godot Reinforcement Learning Agents","created":"2021-12-07","cited_by_count":4,"area":null},{"id":"2306.03530","title":"RLtools: A Fast, Portable Deep Reinforcement Learning Library for Continuous Control","created":"2023-06-06","cited_by_count":4,"area":null},{"id":"2309.16663","title":"HyperPPO: A scalable method for finding small policies for robotic control","created":"2023-09-28","cited_by_count":4,"area":null},{"id":"2312.15204","title":"DexDLO: Learning Goal-Conditioned Dexterous Policy for Dynamic Manipulation of Deformable Linear Objects","created":"2023-12-23","cited_by_count":4,"area":null},{"id":"2502.01366","title":"Trajectory World Models for Heterogeneous Environments","created":"2025-02-03","cited_by_count":4,"area":"wm"},{"id":"2602.01266","title":"Reinforcement Learning for Active Perception in Autonomous Navigation","created":"2026-02-01","cited_by_count":4,"area":"deeprl"},{"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":"2202.07808","title":"Policy Learning and Evaluation with Randomized Quasi-Monte Carlo","created":"2022-02-16","cited_by_count":2,"area":null},{"id":"2401.03993","title":"Behavioural Cloning in VizDoom","created":"2024-01-08","cited_by_count":2,"area":"offlinerl"},{"id":"2408.11816","title":"Efficient Exploration and Discriminative World Model Learning with an Object-Centric Abstraction","created":"2024-08-21","cited_by_count":2,"area":"wm"},{"id":"2411.11318","title":"Syllabus: Portable Curricula for Reinforcement Learning Agents","created":"2024-11-18","cited_by_count":2,"area":"deeprl"},{"id":"2301.00691","title":"Reinforcement Learning with Success Induced Task Prioritization","created":"2022-12-30","cited_by_count":1,"area":null},{"id":"2312.05405","title":"Guaranteed Trust Region Optimization via Two-Phase KL Penalization","created":"2023-12-08","cited_by_count":1,"area":null},{"id":"2406.01939","title":"Speeding up Policy Simulation in Supply Chain RL","created":"2024-06-04","cited_by_count":1,"area":null},{"id":"2410.03565","title":"Training on Irrelevant States Implies Data Augmentation: Generalization in Contextual MDPs","created":"2024-10-04","cited_by_count":1,"area":null},{"id":"2501.01136","title":"Symmetries-enhanced Multi-Agent Reinforcement Learning","created":"2025-01-02","cited_by_count":1,"area":null},{"id":"2501.05408","title":"Tempo: Compiled Dynamic Deep Learning with Symbolic Dependence Graphs","created":"2025-01-09","cited_by_count":1,"area":null},{"id":"2501.12620","title":"Adaptive Data Exploitation in Deep Reinforcement Learning","created":"2025-01-22","cited_by_count":1,"area":"deeprl"},{"id":"2602.15533","title":"Efficient Knowledge Transfer for Jump-Starting Control Policy Learning of Multirotors through Physics-Aware Neural Architectures","created":"2026-02-17","cited_by_count":1,"area":"deeprl"},{"id":"2603.01365","title":"Align and Filter: Improving Performance in Asynchronous On-Policy RL","created":"2026-03-02","cited_by_count":1,"area":null},{"id":"2603.12543","title":"CALF: Communication-Aware Learning Framework for Distributed Reinforcement Learning","created":"2026-03-13","cited_by_count":1,"area":"deeprl"},{"id":"2608.26200","title":"GameWAM: A World Action Model for Video Games","created":"2026-08-25","cited_by_count":1,"area":"wm"},{"id":"2211.15023","title":"AcceRL: Policy Acceleration Framework for Deep Reinforcement Learning","created":"2022-11-28","cited_by_count":0,"area":null},{"id":"2402.05266","title":"A computational approach to visual ecology with deep reinforcement learning","created":"2024-02-07","cited_by_count":0,"area":"deeprl"},{"id":"2407.01310","title":"Multi-State-Action Tokenisation in Decision Transformers for Multi-Discrete Action Spaces","created":"2024-07-01","cited_by_count":0,"area":"offlinerl"},{"id":"2407.09287","title":"Instruction Following with Goal-Conditioned Reinforcement Learning in Virtual Environments","created":"2024-07-12","cited_by_count":0,"area":"lr"},{"id":"2410.24096","title":"Progressive Safeguards for Safe and Model-Agnostic Reinforcement Learning","created":"2024-10-31","cited_by_count":0,"area":"deeprl"},{"id":"2502.20190","title":"Highly Parallelized Reinforcement Learning Training with Relaxed Assignment Dependencies","created":"2025-02-27","cited_by_count":0,"area":"deeprl"},{"id":"2509.19023","title":"Reduced-Order Model-Guided Reinforcement Learning for Demonstration-Free Humanoid Locomotion","created":"2025-09-23","cited_by_count":0,"area":"deeprl"},{"id":"2510.09951","title":"Emergence of Spatial Representation in an Actor-Critic Agent with Hippocampus-Inspired Sequence Generator","created":"2025-10-11","cited_by_count":0,"area":"deeprl"},{"id":"2510.25080","title":"Monopoly Deal: A Benchmark Environment for Bounded One-Sided Response Games","created":"2025-10-29","cited_by_count":0,"area":null},{"id":"2601.18580","title":"K-Myriad: Jump-starting reinforcement learning with unsupervised parallel agents","created":"2026-01-26","cited_by_count":0,"area":"deeprl"},{"id":"2603.01260","title":"MOSAIC: A Universal Agent-Level Interface for Cross-Paradigm Agent Mixing and Human-AI Collaboration","created":"2026-03-01","cited_by_count":0,"area":"agents"},{"id":"2603.12145","title":"Automatic Generation of High-Performance RL Environments","created":"2026-03-12","cited_by_count":0,"area":"deeprl"},{"id":"2603.22182","title":"Cross-Modal Reinforcement Learning for Navigation with Degraded Depth Measurements","created":"2026-03-23","cited_by_count":0,"area":"deeprl"},{"id":"2604.24558","title":"Hierarchical Behaviour Spaces","created":"2026-04-27","cited_by_count":0,"area":"deeprl"},{"id":"2606.20491","title":"Fast Human Attention Prediction for Fixation-guided Active Perception in Autonomous Navigation","created":"2026-06-18","cited_by_count":0,"area":null},{"id":"2606.21587","title":"FAST: A Framework for Aligned Sampling and Training in Parallel Reinforcement Learning for Autonomous Driving","created":"2026-06-19","cited_by_count":0,"area":"driving"},{"id":"2607.26059","title":"Emergent Sparsity in Frozen Random CNN Feature Extractors for Deep Reinforcement Learning","created":"2026-05-15","cited_by_count":0,"area":"deeprl"},{"id":"2608.17641","title":"rl-triton: High-Performance Triton GPU Kernels for Reinforcement Learning Credit Assignment","created":"2026-08-18","cited_by_count":0,"area":"deeprl"},{"id":"2609.09059","title":"PlayTrain: An Efficient Reinforcement Learning Framework for LLM-Generated Adaptable JavaScript Games","created":"2026-09-08","cited_by_count":0,"area":null},{"id":"2609.34422","title":"Coding Agent Memory Post-training: Unlocking the Memory Potential of Pre-trained File Operations for Long-Horizon Tasks via Reinforcement Learning","created":"2026-09-28","cited_by_count":0,"area":"lr"},{"id":"2610.05935","title":"ThunderSyncRL: Lossless Acceleration of Agentic Reinforcement Learning","created":"2026-10-05","cited_by_count":0,"area":"agents"},{"id":"2610.16302","title":"RAR: Rate-Adaptive Rollout for Time-Consistent Interactive World Models","created":"2026-10-12","cited_by_count":0,"area":"wm"}],"next_cursor":null}