Buchumschlag

Align and Filter: Improving Performance in Asynchronous On-Policy RL

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Honari, Homayoun, Castanyer, Roger Creus, Przystupa, Michael, Noukhovitch, Michael, Castro, Pablo Samuel, Berseth, Glen
Format:	Preprint
Veröffentlicht:	2026
Schlagworte:	Machine Learning Artificial Intelligence Robotics Systems and Control
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

Safety Optimized Reinforcement Learning via Multi-Objective Policy Optimization
von: Honari, Homayoun, et al.
Veröffentlicht: (2024)

Agentick: A Unified Benchmark for General Sequential Decision-Making Agents
von: Castanyer, Roger Creus, et al.
Veröffentlicht: (2026)

Improving Intrinsic Exploration by Creating Stationary Objectives
von: Castanyer, Roger Creus, et al.
Veröffentlicht: (2023)

Meta SAC-Lag: Towards Deployable Safe Reinforcement Learning via MetaGradient-based Hyperparameter Tuning
von: Honari, Homayoun, et al.
Veröffentlicht: (2024)

Reinforcement Learning for Versatile, Dynamic, and Robust Bipedal Locomotion Control
von: Li, Zhongyu, et al.
Veröffentlicht: (2024)

ARM-FM: Automated Reward Machines via Foundation Models for Compositional Reinforcement Learning
von: Castanyer, Roger Creus, et al.
Veröffentlicht: (2025)

Surprise-Adaptive Intrinsic Motivation for Unsupervised Reinforcement Learning
von: Hugessen, Adriana, et al.
Veröffentlicht: (2024)

Safe Large-Scale Robust Nonlinear MPC in Milliseconds via Reachability-Constrained System Level Synthesis on the GPU
von: Fang, Jeffrey, et al.
Veröffentlicht: (2026)

CBF-RL: Safety Filtering Reinforcement Learning in Training with Control Barrier Functions
von: Yang, Lizhi, et al.
Veröffentlicht: (2025)

VLA-RAIL: A Real-Time Asynchronous Inference Linker for VLA Models and Robots
von: Zhao, Yongsheng, et al.
Veröffentlicht: (2025)

Q-learning-based Model-free Safety Filter
von: Sue, Guo Ning, et al.
Veröffentlicht: (2024)

Parallel Differentiable Reachability for Learning and Planning with Certified Neural Dynamics and Controllers
von: Shen, Keyi, et al.
Veröffentlicht: (2026)

RL + Model-based Control: Using On-demand Optimal Control to Learn Versatile Legged Locomotion
von: Kang, Dongho, et al.
Veröffentlicht: (2023)

Learning Team-Based Navigation: A Review of Deep Reinforcement Learning Techniques for Multi-Agent Pathfinding
von: Chung, Jaehoon, et al.
Veröffentlicht: (2023)

Improving Pre-Trained Vision-Language-Action Policies with Model-Based Search
von: Neary, Cyrus, et al.
Veröffentlicht: (2025)

Scalable Data-Driven Reachability Analysis and Control via Koopman Operators with Conformal Coverage Guarantees
von: Nath, Devesh, et al.
Veröffentlicht: (2026)

AutoRL Hyperparameter Landscapes
von: Mohan, Aditya, et al.
Veröffentlicht: (2023)

Reliable and Scalable Robot Policy Evaluation with Imperfect Simulators
von: Badithela, Apurva, et al.
Veröffentlicht: (2025)

Active Constraint Learning in High Dimensions from Demonstrations
von: Qiu, Zheng, et al.
Veröffentlicht: (2025)

On-Policy Distillation of Language Models for Autonomous Vehicle Motion Planning
von: Afsharrad, Amirhossein, et al.
Veröffentlicht: (2026)

Generative Predictive Control: Flow Matching Policies for Dynamic and Difficult-to-Demonstrate Tasks
von: Kurtz, Vince, et al.
Veröffentlicht: (2025)

Probabilistic Satisfaction of Temporal Logic Constraints in Reinforcement Learning via Adaptive Policy-Switching
von: Lin, Xiaoshan, et al.
Veröffentlicht: (2024)

Confidence-Aware Decision-Making and Control for Tool Selection
von: Meera, Ajith Anil, et al.
Veröffentlicht: (2024)

Scaling Verification Can Be More Effective than Scaling Policy Learning for Vision-Language-Action Alignment
von: Kwok, Jacky, et al.
Veröffentlicht: (2026)

Improving the Resilience of Quadrotors in Underground Environments by Combining Learning-based and Safety Controllers
von: Ward, Isaac Ronald, et al.
Veröffentlicht: (2025)

Mission-Aligned Learning-Informed Control of Autonomous Systems: Formulation and Foundations
von: Kungurtsev, Vyacheslav, et al.
Veröffentlicht: (2025)

Intelligent Electric Power Steering: Artificial Intelligence Integration Enhances Vehicle Safety and Performance
von: Vyas, Vikas, et al.
Veröffentlicht: (2024)

Human-in-the-Loop Pareto Optimization: Trade-off Characterization for Assist-as-Needed Training and Performance Evaluation
von: Tolasa, Harun, et al.
Veröffentlicht: (2026)

Design and Realization of a Benchmarking Testbed for Evaluating Autonomous Platooning Algorithms
von: Shaham, Michael, et al.
Veröffentlicht: (2024)

Visual CPG-RL: Learning Central Pattern Generators for Visually-Guided Quadruped Locomotion
von: Bellegarda, Guillaume, et al.
Veröffentlicht: (2022)

End-to-end deep learning-based framework for path planning and collision checking: bin picking application
von: Tamizi, Mehran Ghafarian, et al.
Veröffentlicht: (2023)

Enhanced-FQL($λ$), an Efficient and Interpretable RL with novel Fuzzy Eligibility Traces and Segmented Experience Replay
von: Jalaeian-Farimani, Mohsen, et al.
Veröffentlicht: (2026)

MAGICS: Adversarial RL with Minimax Actors Guided by Implicit Critic Stackelberg for Convergent Neural Synthesis of Robot Safety
von: Wang, Justin, et al.
Veröffentlicht: (2024)

Digital Twin Synchronization: Bridging the Sim-RL Agent to a Real-Time Robotic Additive Manufacturing Control
von: Ali, Matsive, et al.
Veröffentlicht: (2025)

ASAP: Aligning Simulation and Real-World Physics for Learning Agile Humanoid Whole-Body Skills
von: He, Tairan, et al.
Veröffentlicht: (2025)

One Filter to Deploy Them All: Robust Safety for Quadrupedal Navigation in Unknown Environments
von: Lin, Albert, et al.
Veröffentlicht: (2024)

Statistically Assuring Safety of Control Systems using Ensembles of Safety Filters and Conformal Prediction
von: Tabbara, Ihab, et al.
Veröffentlicht: (2025)

CLIP-RLDrive: Human-Aligned Autonomous Driving via CLIP-Based Reward Shaping in Reinforcement Learning
von: Doroudian, Erfan, et al.
Veröffentlicht: (2024)

Efficient On-policy Visual-RL via Stochastic Decoupled Policy Gradient
von: You, Haoxiang, et al.
Veröffentlicht: (2026)

Performance-Aware Self-Configurable Multi-Agent Networks: A Distributed Submodular Approach for Simultaneous Coordination and Network Design
von: Xu, Zirui, et al.
Veröffentlicht: (2024)