paper-with-me

홈 › Papers

MEET: A Monte Carlo Exploration-Exploitation Trade-off for Buffer Sampling

2022-10-24 · Julius Ott, Lorenzo Servadei, Jose Arjona-Medina, Enrico Rinaldi, Gianfranco Mauro, Daniela Sánchez Lopera, Michael Stephan, Thomas Stadelmayer, Avik Santra, Robert Wille

Data selection is essential for any data-based optimization technique, such as Reinforcement Learning. State-of-the-art sampling strategies for the experience replay buffer improve the performance of the Reinforcement Learning agent. However, they do not incorporate uncertainty in the Q-Value estimation. Consequently, they cannot adapt the sampling strategies, including exploration and exploitation of transitions, to the complexity of the task. To address this, this paper proposes a new sampling strategy that leverages the exploration-exploitation trade-off. This is enabled by the uncertainty estimation of the Q-Value function, which guides the sampling to explore more significant transitions and, thus, learn a more efficient policy. Experiments on classical control environments demonstrate stable results across various environments. They show that the proposed method outperforms state-of-the-art sampling strategies for dense rewards w.r.t. convergence and peak performance by 26% on average.

📄 PDF Abstract BibTeX arXiv:2210.13545

Code (1)

juliusott/uncertainty-buffer 공식 구현 pytorch

Tasks

reinforcement-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

When LLM Meets Tree Search: A Systematic View of Inference as Search in Large Language Models

2026-08-31 · Jiaqi Wei, Xiang Zhang, Yuejin Yang, Wenxuan Huang 외 arxiv

As pretraining scaling laws approach saturation, Test-Time Scaling (TTS) has emerged as an important direction for improving reasoning by allocating inference-time compute to a fixed model prior. Viewed at a high level, …

Monte-Carlo Tree Search for Policy Optimization

2019-12-23 · Xiaobai Ma, Katherine Driggs-Campbell, Zongzhang Zhang, Mykel J. Kochenderfer

Gradient-based methods are often used for policy optimization in deep reinforcement learning, despite being vulnerable to local optima and saddle points. Although gradient-free methods (e.g., genetic algorithms or evolut…

Deep Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Watch the Unobserved: A Simple Approach to Parallelizing Monte Carlo Tree Search

2018-10-28 · ICLR 2020 1 · Anji Liu, Jianshu Chen, Mingze Yu, Yu Zhai 외

Monte Carlo Tree Search (MCTS) algorithms have achieved great success on many challenging benchmarks (e.g., Computer Go). However, they generally require a large number of rollouts, making their applications costly. Furt…

REFINING MONTE CARLO TREE SEARCH AGENTS BY MONTE CARLO TREE SEARCH

2019-09-25 · Katsuki Ohto

Reinforcement learning methods that continuously learn neural networks by episode generation with game tree search have been successful in two-person complete information deterministic games such as chess, shogi, and Go.…

reinforcement-learningReinforcement Learning (RL)

Monte Carlo Tree Diffusion for System 2 Planning

2025-02-11 · Jaesik Yoon, Hyeonseo Cho, Doojin Baek, Yoshua Bengio 외

Diffusion models have recently emerged as a powerful tool for planning. However, unlike Monte Carlo Tree Search (MCTS)-whose performance naturally improves with additional test-time computation (TTC), standard diffusion-…

Denoising