paper-with-me

Papers

Regret Minimization Experience Replay in Off-Policy Reinforcement Learning

2021-05-15 · NeurIPS 2021 12 · Xu-Hui Liu, Zhenghai Xue, Jing-Cheng Pang, Shengyi Jiang, Feng Xu, Yang Yu

In reinforcement learning, experience replay stores past samples for further reuse. Prioritized sampling is a promising technique to better utilize these samples. Previous criteria of prioritization include TD error, recentness and corrective feedback, which are mostly heuristically designed. In this work, we start from the regret minimization objective, and obtain an optimal prioritization strategy for Bellman update that can directly maximize the return of the policy. The theory suggests that data with higher hindsight TD error, better on-policiness and more accurate Q value should be assigned with higher weights during sampling. Thus most previous criteria only consider this strategy partially. We not only provide theoretical justifications for previous criteria, but also propose two new methods to compute the prioritization weight, namely ReMERN and ReMERT. ReMERN learns an error network, while ReMERT exploits the temporal ordering of states. Both methods outperform previous prioritized sampling algorithms in challenging RL benchmarks, including MuJoCo, Atari and Meta-World.

📄 PDF Abstract BibTeX arXiv:2105.07253

Code (1)

aidefender/remern-remert 공식 구현

Tasks

MuJoCoreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Methods 이 논문이 사용한 방법론

Experience Replay Experience Replay is a replay memory technique used in reinforcement learning where we store the agent’s experiences at each time-step, $e\_{t} = \left(s\_{t}, a\_{t}, r\_{t},…

Similar Papers 제목 키워드 기반

MAC-PO: Multi-Agent Experience Replay via Collective Priority Optimization

2023-02-21 · Yongsheng Mei, Hanhan Zhou, Tian Lan, Guru Venkataramani 외

Experience replay is crucial for off-policy reinforcement learning (RL) methods. By remembering and reusing the experiences from past different policies, experience replay significantly improves the training efficiency a…

Decision MakingMulti-agent Reinforcement Learningreinforcement-learningReinforcement Learning+2

Adaptive Experience Selection for Policy Gradient

2020-02-17 · Saad Mohamad, Giovanni Montana

Policy gradient reinforcement learning (RL) algorithms have achieved impressive performance in challenging learning tasks such as continuous control, but suffer from high sample complexity. Experience replay is a commonl…

continuous-controlContinuous ControlOpenAI GymReinforcement Learning+1

Experience Replay Optimization

2019-06-19 · Daochen Zha, Kwei-Herng Lai, Kaixiong Zhou, Xia Hu

Experience replay enables reinforcement learning agents to memorize and reuse past experiences, just as humans replay memories for the situation at hand. Contemporary off-policy algorithms either replay past experiences …

continuous-controlContinuous Controlreinforcement-learningReinforcement Learning+1

Enhancing Deep Deterministic Policy Gradients on Continuous Control Tasks with Decoupled Prioritized Experience Replay

2025-12-04 · Mehmet Efe Lorasdagi, Dogan Can Cicek, Furkan Burak Mutlu, Suleyman Serdar Kozat arxiv

Background: Deep Deterministic Policy Gradient-based reinforcement learning algorithms utilize Actor-Critic architectures, where both networks are typically trained using identical batches of replayed transitions. Howeve…

Reinforcement LearningContinuous ControlOpenAI Gym

Improved Regret Bound and Experience Replay in Regularized Policy Iteration

2021-02-25 · Nevena Lazic, Dong Yin, Yasin Abbasi-Yadkori, Csaba Szepesvari

In this work, we study algorithms for learning in infinite-horizon undiscounted Markov decision processes (MDPs) with function approximation. We first show that the regret analysis of the Politex algorithm (a version of …