Imagen de Portada

Staggered Environment Resets Improve Massively Parallel On-Policy Reinforcement Learning

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Bharthulwar, Sid, Tao, Stone, Su, Hao
Formato:	Preprint
Publicado:	2025
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Reverse Forward Curriculum Learning for Extreme Sample and Demonstration Efficiency in Reinforcement Learning
por: Tao, Stone, et al.
Publicado: (2024)

The Power of Resets in Online Reinforcement Learning
por: Mhammedi, Zakaria, et al.
Publicado: (2024)

A Reinforcement Learning based Reset Policy for CDCL SAT Solvers
por: Li, Chunxiao, et al.
Publicado: (2024)

Stochastic Resetting Accelerates Policy Convergence in Reinforcement Learning
por: Zhou, Jello, et al.
Publicado: (2026)

Enabling Realtime Reinforcement Learning at Scale with Staggered Asynchronous Inference
por: Riemer, Matthew, et al.
Publicado: (2024)

Multi-Stage Manipulation with Demonstration-Augmented Reward, Policy, and World Model Learning
por: Escoriza, Adrià López, et al.
Publicado: (2025)

Policy Decorator: Model-Agnostic Online Refinement for Large Policy Model
por: Yuan, Xiu, et al.
Publicado: (2024)

StagFormer: Time Staggering Transformer Decoding for RunningLayers In Parallel
por: Cutler, Dylan, et al.
Publicado: (2025)

On the Reuse Bias in Off-Policy Reinforcement Learning
por: Ying, Chengyang, et al.
Publicado: (2022)

Dataset Reset Policy Optimization for RLHF
por: Chang, Jonathan D., et al.
Publicado: (2024)

Evolutionary Prompt Optimization Discovers Emergent Multimodal Reasoning Strategies in Vision-Language Models
por: Bharthulwar, Sid, et al.
Publicado: (2025)

Beyond Verifiable Rewards: Scaling Reinforcement Learning for Language Models to Unverifiable Data
por: Tang, Yunhao, et al.
Publicado: (2025)

The Impact of On-Policy Parallelized Data Collection on Deep Reinforcement Learning Networks
por: Mayor, Walter, et al.
Publicado: (2025)

Reset & Distill: A Recipe for Overcoming Negative Transfer in Continual Reinforcement Learning
por: Ahn, Hongjoon, et al.
Publicado: (2024)

Safe Reinforcement Learning using Action Projection: Safeguard the Policy or the Environment?
por: Markgraf, Hannah, et al.
Publicado: (2025)

ManiSkill-HAB: A Benchmark for Low-Level Manipulation in Home Rearrangement Tasks
por: Shukla, Arth, et al.
Publicado: (2024)

Improving Policy Exploitation in Online Reinforcement Learning with Instant Retrospect Action
por: Gao, Gong, et al.
Publicado: (2026)

Massively Parallel Expectation Maximization For Approximate Posteriors
por: Heap, Thomas, et al.
Publicado: (2025)

Massively Parallel Exact Inference for Hawkes Processes
por: Raza, Ahmer, et al.
Publicado: (2026)

Interpret Policies in Deep Reinforcement Learning using SILVER with RL-Guided Labeling: A Model-level Approach to High-dimensional and Multi-action Environments
por: Qian, Yiyu, et al.
Publicado: (2025)

POLAR: Policy-based Layerwise Reinforcement Learning Method for Stealthy Backdoor Attacks in Federated Learning
por: Yu, Kuai, et al.
Publicado: (2025)

Massively Scalable Inverse Reinforcement Learning in Google Maps
por: Barnes, Matt, et al.
Publicado: (2023)

How Ensembles of Distilled Policies Improve Generalisation in Reinforcement Learning
por: Weltevrede, Max, et al.
Publicado: (2025)

Self-Normalized Resets for Plasticity in Continual Learning
por: Farias, Vivek F., et al.
Publicado: (2024)

Toward Information Theoretic Active Inverse Reinforcement Learning
por: Bajgar, Ondrej, et al.
Publicado: (2024)

Exchangeable Gaussian Processes for Staggered-Adoption Policy Evaluation
por: Gevorgyan, Hayk, et al.
Publicado: (2026)

Learning Massively Multitask World Models for Continuous Control
por: Hansen, Nicklas, et al.
Publicado: (2025)

To Switch or Not to Switch? Balanced Policy Switching in Offline Reinforcement Learning
por: Ma, Tao, et al.
Publicado: (2024)

Learning Without Time-Based Embodiment Resets in Soft-Actor Critic
por: Farrahi, Homayoon, et al.
Publicado: (2025)

Policy-Based Trajectory Clustering in Offline Reinforcement Learning
por: Hu, Hao, et al.
Publicado: (2025)

On-Policy Policy Gradient Reinforcement Learning Without On-Policy Sampling
por: Corrado, Nicholas E., et al.
Publicado: (2023)

Policy Improvement Reinforcement Learning
por: Wang, Huaiyang, et al.
Publicado: (2026)

Flow-Based Policy for Online Reinforcement Learning
por: Lv, Lei, et al.
Publicado: (2025)

Scaling Policy Gradient Quality-Diversity with Massive Parallelization via Behavioral Variations
por: Mitsides, Konstantinos, et al.
Publicado: (2025)

Dyna-LfLH: Learning Agile Navigation in Dynamic Environments from Learned Hallucination
por: Ghani, Saad Abdul, et al.
Publicado: (2024)

ReinFlow: Fine-tuning Flow Matching Policy with Online Reinforcement Learning
por: Zhang, Tonghe, et al.
Publicado: (2025)

Mastering Massive Multi-Task Reinforcement Learning via Mixture-of-Expert Decision Transformer
por: Kong, Yilun, et al.
Publicado: (2025)

Federated Reinforcement Learning in Heterogeneous Environments
por: Hwang, Ukjo, et al.
Publicado: (2025)

Discovering Minimal Reinforcement Learning Environments
por: Liesen, Jarek, et al.
Publicado: (2024)

Synthetic Monitoring Environments for Reinforcement Learning
por: Pleiss, Leonard, et al.
Publicado: (2026)