{"total":78,"rows":[{"id":"2410.12557","title":"One Step Diffusion via Shortcut Models","created":"2024-10-16","cited_by_count":391,"area":"diffusion"},{"id":"2403.03950","title":"Stop Regressing: Training Value Functions via Classification for Scalable Deep RL","created":"2024-03-06","cited_by_count":144,"area":"deeprl"},{"id":"2405.16158","title":"Bigger, Regularized, Optimistic: scaling for compute and sample-efficient continuous control","created":"2024-05-25","cited_by_count":108,"area":"deeprl"},{"id":"2503.07137","title":"A Comprehensive Survey of Mixture-of-Experts: Algorithms, Theory, and Applications","created":"2025-03-10","cited_by_count":91,"area":"moe"},{"id":"2410.09754","title":"SimBa: Simplicity Bias for Scaling Up Parameters in Deep Reinforcement Learning","created":"2024-10-13","cited_by_count":76,"area":"deeprl"},{"id":"2504.11054","title":"Zero-Shot Whole-Body Humanoid Control via Behavioral Foundation Models","created":"2025-04-15","cited_by_count":56,"area":"deeprl"},{"id":"2412.12953","title":"Efficient Diffusion Transformer Policies with Mixture of Expert Denoisers for Multitask Learning","created":"2024-12-17","cited_by_count":48,"area":"diffusion"},{"id":"2410.23208","title":"Kinetix: Investigating the Training of General Agents through Open-Ended Physics-Based Control Tasks","created":"2024-10-30","cited_by_count":45,"area":null},{"id":"2503.14858","title":"1000 Layer Networks for Self-Supervised RL: Scaling Depth Can Enable New Goal-Reaching Capabilities","created":"2025-03-19","cited_by_count":45,"area":"deeprl"},{"id":"2402.12479","title":"In value-based deep reinforcement learning, a pruned network is a good network","created":"2024-02-19","cited_by_count":39,"area":"deeprl"},{"id":"2404.09134","title":"Generative AI Agents with Large Language Model for Satellite Networks via a Mixture of Experts Transmission","created":"2024-04-14","cited_by_count":35,"area":"agents"},{"id":"2403.13358","title":"GeRM: A Generalist Robotic Model with Mixture-of-experts for Quadruped Robot","created":"2024-03-20","cited_by_count":29,"area":"moe"},{"id":"2405.13997","title":"Sigmoid Gating is More Sample Efficient than Softmax Gating in Mixture of Experts","created":"2024-05-22","cited_by_count":24,"area":"moe"},{"id":"2411.04832","title":"Plasticity Loss in Deep Reinforcement Learning: A Survey","created":"2024-11-07","cited_by_count":24,"area":"deeprl"},{"id":"2410.07265","title":"A Survey: Collaborative Hardware and Software Design in the Era of Large Language Models","created":"2024-10-08","cited_by_count":23,"area":null},{"id":"2503.08564","title":"MoE-Loco: Mixture of Experts for Multitask Locomotion","created":"2025-03-11","cited_by_count":23,"area":"moe"},{"id":"2506.15544","title":"Stable Gradients for Stable Learning at Scale in Deep Reinforcement Learning","created":"2025-06-18","cited_by_count":23,"area":"deeprl"},{"id":"2509.06863","title":"floq: Training Critics via Flow-Matching for Scaling Compute in Value-Based RL","created":"2025-09-08","cited_by_count":22,"area":"diffusion"},{"id":"2406.17523","title":"On the consistency of hyper-parameter selection in value-based deep reinforcement learning","created":"2024-06-25","cited_by_count":21,"area":"deeprl"},{"id":"2406.18420","title":"Mixture of Experts in a Mixture of RL settings","created":"2024-06-26","cited_by_count":21,"area":"moe"},{"id":"2410.07994","title":"Neuroplastic Expansion in Deep Reinforcement Learning","created":"2024-10-10","cited_by_count":18,"area":"deeprl"},{"id":"2505.24378","title":"Mastering Massive Multi-Task Reinforcement Learning via Mixture-of-Expert Decision Transformer","created":"2025-05-30","cited_by_count":15,"area":"moe"},{"id":"2410.01930","title":"Don't flatten, tokenize! Unlocking the key to SoftMoE's efficacy in deep RL","created":"2024-10-02","cited_by_count":14,"area":"deeprl"},{"id":"2505.24061","title":"Measure gradients, not activations! Enhancing neuronal activity in deep reinforcement learning","created":"2025-05-29","cited_by_count":14,"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":"2510.13704","title":"Simplicial Embeddings Improve Sample Efficiency in Actor-Critic Agents","created":"2025-10-15","cited_by_count":12,"area":"deeprl"},{"id":"2406.17949","title":"The Overcooked Generalisation Challenge: Evaluating Cooperation with Novel Partners in Unknown Environments Using Unsupervised Environment Design","created":"2024-06-25","cited_by_count":11,"area":"deeprl"},{"id":"2506.17204","title":"Network Sparsity Unlocks the Scaling Potential of Deep Reinforcement Learning","created":"2025-06-20","cited_by_count":11,"area":"deeprl"},{"id":"2502.17666","title":"Yes, Q-learning Helps Offline In-Context RL","created":"2025-02-24","cited_by_count":10,"area":"offlinerl"},{"id":"2410.05026","title":"Active Fine-Tuning of Multi-Task Policies","created":"2024-10-07","cited_by_count":9,"area":"offlinerl"},{"id":"2602.01439","title":"TQL: Scaling Q-Functions with Transformers by Preventing Attention Collapse","created":"2026-02-01","cited_by_count":9,"area":"deeprl"},{"id":"2503.05126","title":"Multi-Task Reinforcement Learning Enables Parameter Scaling","created":"2025-03-07","cited_by_count":8,"area":"deeprl"},{"id":"2506.05426","title":"Mixture-of-Experts Meets In-Context Reinforcement Learning","created":"2025-06-05","cited_by_count":8,"area":"moe"},{"id":"2503.23478","title":"Handling Delay in Real-Time Reinforcement Learning","created":"2025-03-30","cited_by_count":7,"area":"deeprl"},{"id":"2505.15345","title":"Hadamax Encoding: Elevating Performance in Model-Free Atari","created":"2025-05-21","cited_by_count":7,"area":"deeprl"},{"id":"2503.05546","title":"Impoola: The Power of Average Pooling for Image-Based Deep Reinforcement Learning","created":"2025-03-07","cited_by_count":6,"area":"deeprl"},{"id":"2506.13672","title":"The Courage to Stop: Overcoming Sunk Cost Fallacy in Deep Reinforcement Learning","created":"2025-06-16","cited_by_count":6,"area":"deeprl"},{"id":"2410.23810","title":"CALE: Continuous Arcade Learning Environment","created":"2024-10-31","cited_by_count":5,"area":null},{"id":"2602.19373","title":"Stable Deep Reinforcement Learning via Isotropic Gaussian Representations","created":"2026-02-22","cited_by_count":5,"area":"deeprl"},{"id":"2501.12670","title":"Celo: Training Versatile Learned Optimizers on a Compute Diet","created":"2025-01-22","cited_by_count":4,"area":null},{"id":"2503.03213","title":"Convergence Rates for Softmax Gating Mixture of Experts","created":"2025-03-05","cited_by_count":4,"area":"moe"},{"id":"2505.17749","title":"Mind the GAP! The Challenges of Scale in Pixel-based Deep Reinforcement Learning","created":"2025-05-23","cited_by_count":4,"area":"deeprl"},{"id":"2506.04398","title":"Bridging the Performance Gap Between Target-Free and Target-Based Reinforcement Learning","created":"2025-06-04","cited_by_count":4,"area":"deeprl"},{"id":"2412.13053","title":"SMOSE: Sparse Mixture of Shallow Experts for Interpretable Reinforcement Learning in Continuous Control Tasks","created":"2024-12-17","cited_by_count":3,"area":"deeprl"},{"id":"2509.07945","title":"One Model for All Tasks: Leveraging Efficient World Models in Multi-Task Planning","created":"2025-09-09","cited_by_count":3,"area":"wm"},{"id":"2603.06009","title":"Preventing Learning Stagnation in PPO by Scaling to 1 Million Parallel Environments","created":"2026-03-06","cited_by_count":3,"area":null},{"id":"2507.07197","title":"Combining Pre-Trained Models for Enhanced Feature Representation in Reinforcement Learning","created":"2025-07-09","cited_by_count":2,"area":"deeprl"},{"id":"2508.06871","title":"Sparsity-Driven Plasticity in Multi-Task Reinforcement Learning","created":"2025-08-09","cited_by_count":2,"area":"deeprl"},{"id":"2605.04712","title":"SPHERE: Mitigating the Loss of Spectral Plasticity in Mixture-of-Experts for Deep Reinforcement Learning","created":"2026-05-06","cited_by_count":2,"area":"moe"},{"id":"2406.09079","title":"Hadamard Representation: Scaffolding Performance Across Model-free RL","created":"2024-06-13","cited_by_count":1,"area":"deeprl"},{"id":"2505.18455","title":"On Minimax Estimation of Parameters in Softmax-Contaminated Mixture of Experts","created":"2025-05-24","cited_by_count":1,"area":"moe"},{"id":"2506.11706","title":"Growing with Experience: Growing Neural Networks in Deep Reinforcement Learning","created":"2025-06-13","cited_by_count":1,"area":"deeprl"},{"id":"2508.01329","title":"Is Exploration or Optimization the Problem for Deep Reinforcement Learning?","created":"2025-08-02","cited_by_count":1,"area":"deeprl"},{"id":"2508.03194","title":"Scaling DRL for Decision Making: A Survey on Data, Network, and Training Budget Strategies","created":"2025-08-05","cited_by_count":1,"area":null},{"id":"2509.06355","title":"A Data-Driven Discretized CS:GO Simulation Environment to Facilitate Strategic Multi-Agent Planning Research","created":"2025-09-08","cited_by_count":1,"area":null},{"id":"2510.12096","title":"Rethinking the Role of Dynamic Sparse Training for Scalable Deep Reinforcement Learning","created":"2025-10-14","cited_by_count":1,"area":"deeprl"},{"id":"2511.08234","title":"Beyond Distributions: Geometric Action Control for Continuous Reinforcement Learning","created":"2025-11-11","cited_by_count":1,"area":"deeprl"},{"id":"2512.23773","title":"FineFT: Efficient and Risk-Aware Ensemble Reinforcement Learning for Futures Trading","created":"2025-12-29","cited_by_count":1,"area":"deeprl"},{"id":"2603.08476","title":"LAR-MoE: Latent-Aligned Routing for Mixture of Experts in Robotic Imitation Learning","created":"2026-03-09","cited_by_count":1,"area":"offlinerl"},{"id":"2606.20411","title":"Direct Advantage Estimation for Scalable and Sample-efficient Deep Reinforcement Learning","created":"2026-06-18","cited_by_count":1,"area":"deeprl"},{"id":"2609.12531","title":"Temporal Recurrence Favors Fewer Layers","created":"2026-09-11","cited_by_count":1,"area":null},{"id":"2506.12453","title":"Topology-Assisted Spatio-Temporal Pattern Disentangling for Scalable MARL in Large-scale Autonomous Traffic Control","created":"2025-06-14","cited_by_count":0,"area":null},{"id":"2511.08241","title":"PrefPoE: Advantage-Guided Preference Fusion for Learning Where to Explore","created":"2025-11-11","cited_by_count":0,"area":"deeprl"},{"id":"2512.13727","title":"RAST-MoE-RL: A Regime-Aware Spatio-Temporal MoE Framework for Deep Reinforcement Learning in Ride-Hailing","created":"2025-12-13","cited_by_count":0,"area":"moe"},{"id":"2602.00939","title":"Improving Minimax Estimation Rates for Contaminated Mixture of Multinomial Logistic Experts via Expert Heterogeneity","created":"2026-01-31","cited_by_count":0,"area":"moe"},{"id":"2602.19244","title":"Robust Exploration in Directed Controller Synthesis via Reinforcement Learning with Soft Mixture-of-Experts","created":"2026-02-22","cited_by_count":0,"area":"moe"},{"id":"2604.12909","title":"Tree Learning: A Multi-Skill Continual Learning Framework for Humanoid Robots","created":"2026-04-14","cited_by_count":0,"area":"deeprl"},{"id":"2605.10546","title":"Higher Resolution, Better Generalization: Unlocking Visual Scaling in Deep Reinforcement Learning","created":"2026-05-11","cited_by_count":0,"area":"deeprl"},{"id":"2605.21557","title":"Scalable Reinforcement Learning via Adaptive Batch Scaling","created":"2026-05-20","cited_by_count":0,"area":"deeprl"},{"id":"2605.27722","title":"NUCLEUS-MoE: Unified Model of Pool Boiling for Liquid Cooling","created":"2026-05-26","cited_by_count":0,"area":"moe"},{"id":"2606.03382","title":"Local Guidance, Global Impact: Gaussian-Reshaped Trust Region Unlocks Behavior Transitions","created":"2026-06-02","cited_by_count":0,"area":"deeprl"},{"id":"2606.05555","title":"Representation Learning Enables Scalable Multitask Deep Reinforcement Learning","created":"2026-06-04","cited_by_count":0,"area":"deeprl"},{"id":"2606.21136","title":"Horizon Adaptive Offline Policy Learning via Value Stitching","created":"2026-06-19","cited_by_count":0,"area":"offlinerl"},{"id":"2608.07870","title":"V-Simba: Unleashing the Architectural Potential of RL in Visual Continuous Control","created":"2026-08-08","cited_by_count":0,"area":"deeprl"},{"id":"2609.04807","title":"CoLMIN: LLM-based Multi-Decision Path Negotiation for Cooperative Autonomous Driving","created":"2026-09-04","cited_by_count":0,"area":null},{"id":"2609.31281","title":"MA-WAM: Multi-Agent World-Action Model for Test-Time Planning","created":"2026-09-25","cited_by_count":0,"area":"wm"},{"id":"2610.17007","title":"Mixture of GFlowNets","created":"2026-10-12","cited_by_count":0,"area":null},{"id":"2610.20009","title":"Outperforming 1000 Euclidean Layers With Hyperbolic Goal-Conditioned RL","created":"2026-10-14","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}