paper-with-me

Papers

One Policy is Enough: Parallel Exploration with a Single Policy is Near-Optimal for Reward-Free Reinforcement Learning

2022-05-31 · Pedro Cisneros-Velarde, Boxiang Lyu, Sanmi Koyejo, Mladen Kolar

Although parallelism has been extensively used in reinforcement learning (RL), the quantitative effects of parallel exploration are not well understood theoretically. We study the benefits of simple parallel exploration for reward-free RL in linear Markov decision processes (MDPs) and two-player zero-sum Markov games (MGs). In contrast to the existing literature, which focuses on approaches that encourage agents to explore a diverse set of policies, we show that using a single policy to guide exploration across all agents is sufficient to obtain an almost-linear speedup in all cases compared to their fully sequential counterpart. Furthermore, we demonstrate that this simple procedure is near-minimax optimal in the reward-free setting for linear MDPs. From a practical perspective, our paper shows that a single policy is sufficient and provably near-optimal for incorporating parallelism during the exploration phase.

📄 PDF Abstract BibTeX arXiv:2205.15891

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning (RL)

Similar Papers 제목 키워드 기반

Rethinking Policy Diversity in Ensemble Policy Gradient in Large-Scale Reinforcement Learning

2026-03-02 · Naoki Shitanda, Motoki Omura, Tatsuya Harada, Takayuki Osa arxiv

Scaling reinforcement learning to tens of thousands of parallel environments requires overcoming the limited exploration capacity of a single policy. Ensemble-based policy gradient methods, which employ multiple policies…

Reinforcement Learning

Colored Noise in PPO: Improved Exploration and Performance through Correlated Action Sampling

2023-12-18 · Jakob Hollenstein, Georg Martius, Justus Piater

Proximal Policy Optimization (PPO), a popular on-policy deep reinforcement learning method, employs a stochastic policy for exploration. In this paper, we propose a colored noise-based stochastic policy variant of PPO. P…

Deep Reinforcement Learningreinforcement-learningReinforcement Learning

Fine-tuning is Not Enough: A Parallel Framework for Collaborative Imitation and Reinforcement Learning in End-to-end Autonomous Driving

2026-03-14 · Zhexi Lian, Haoran Wang, Xuerun Yan, Weimeng Lin 외 arxiv

End-to-end autonomous driving is typically built upon imitation learning (IL), yet its performance is constrained by the quality of human demonstrations. To overcome this limitation, recent methods incorporate reinforcem…

Reinforcement LearningAutonomous Driving

Actor-critic is implicitly biased towards high entropy optimal policies

2021-10-21 · ICLR 2022 4 · Yuzheng Hu, Ziwei Ji, Matus Telgarsky

We show that the simplest actor-critic method -- a linear softmax policy updated with TD through interaction with a linear MDP, but featuring no explicit regularization or exploration -- does not merely find an optimal p…

Vocal Bursts Intensity Prediction

Interactive Parallel Exploration for Reinforcement Learning in Continuous Action Spaces

2018-09-27 · Whiyoung Jung, Giseung Park, Youngchul Sung

In this paper, a new interactive parallel learning scheme is proposed to enhance the performance of off-policy continuous-action reinforcement learning. In the proposed interactive parallel learning scheme, multiple ide…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)