paper-with-me

Papers

Parallel $Q$-Learning: Scaling Off-policy Reinforcement Learning under Massively Parallel Simulation

2023-07-24 · Zechu Li, Tao Chen, Zhang-Wei Hong, Anurag Ajay, Pulkit Agrawal

Reinforcement learning is time-consuming for complex tasks due to the need for large amounts of training data. Recent advances in GPU-based simulation, such as Isaac Gym, have sped up data collection thousands of times on a commodity GPU. Most prior works used on-policy methods like PPO due to their simplicity and ease of scaling. Off-policy methods are more data efficient but challenging to scale, resulting in a longer wall-clock training time. This paper presents a Parallel $Q$-Learning (PQL) scheme that outperforms PPO in wall-clock time while maintaining superior sample efficiency of off-policy learning. PQL achieves this by parallelizing data collection, policy learning, and value learning. Different from prior works on distributed off-policy learning, such as Apex, our scheme is designed specifically for massively parallel GPU-based simulation and optimized to work on a single workstation. In experiments, we demonstrate that $Q$-learning can be scaled to \textit{tens of thousands of parallel environments} and investigate important factors affecting learning speed. The code is available at https://github.com/Improbable-AI/pql.

📄 PDF Abstract BibTeX arXiv:2307.12983

Code (0)

등록된 구현이 없습니다.

Tasks

GPUQ-Learningreinforcement-learning

Methods 이 논문이 사용한 방법론

Entropy Regularization 설명 없음
PPO Proximal Policy Optimization, or PPO, is a policy gradient method for reinforcement learning. The motivation was to have an algorithm with the data efficiency and reliable…

Similar Papers 제목 키워드 기반

Trust-Region Diffusion Policies for Massively Parallel On-Policy RL

2026-06-13 · Huy Le, Onur Celik, Denis Blessing, Tai Hoang 외 arxiv

Reinforcement learning with massively parallel simulations has become a standard framework for developing robust, deployable policies; however, most existing approaches still rely on simple Gaussian policy parameterizati…

Reinforcement Learning

Benchmarking Massively Parallelized Multi-Task Reinforcement Learning for Robotics Tasks

2025-07-31 · Viraj Joshi, Zifan Xu, Bo Liu, Peter Stone 외 arxiv

Multi-task Reinforcement Learning (MTRL) has emerged as a critical training paradigm for applying reinforcement learning (RL) to a set of complex real-world robotic tasks, which demands a generalizable and robust policy.…

Reinforcement Learning

Massively Scaling Explicit Policy-conditioned Value Functions

2025-02-17 · Nico Bohlinger, Jan Peters

We introduce a scaling strategy for Explicit Policy-Conditioned Value Functions (EPVFs) that significantly improves performance on challenging continuous-control tasks. EPVFs learn a value function V({\theta}) that is ex…

continuous-controlContinuous ControlDeep Reinforcement LearningEfficient Exploration+1

Learning to Walk in Minutes Using Massively Parallel Deep Reinforcement Learning

2021-09-24 · Nikita Rudin, David Hoeller, Philipp Reist, Marco Hutter

In this work, we present and study a training set-up that achieves fast policy generation for real-world robotic tasks by using massive parallelism on a single workstation GPU. We analyze and discuss the impact of differ…

Deep Reinforcement LearningGPUreinforcement-learningReinforcement Learning (RL)

Massively Parallel Methods for Deep Reinforcement Learning

2015-07-15 · Arun Nair, Praveen Srinivasan, Sam Blackwell, Cagdas Alcicek 외

We present the first massively distributed architecture for deep reinforcement learning. This architecture uses four main components: parallel actors that generate new behaviour; parallel learners that are trained from s…

Atari GamesDeep Reinforcement Learningreinforcement-learningReinforcement Learning+1