paper-with-me

홈 › Papers

Convergence Guarantees for Deep Epsilon Greedy Policy Learning

2021-12-02 · Michael Rawson, Radu Balan

Policy learning is a quickly growing area. As robotics and computers control day-to-day life, their error rate needs to be minimized and controlled. There are many policy learning methods and bandit methods with provable error rates that accompany them. We show an error or regret bound and convergence of the Deep Epsilon Greedy method which chooses actions with a neural network's prediction. We also show that Epsilon Greedy method regret upper bound is minimized with cubic root exploration. In experiments with the real-world dataset MNIST, we construct a nonlinear reinforcement learning problem. We witness how with either high or low noise, some methods do and some do not converge which agrees with our proof of convergence.

📄 PDF Abstract BibTeX arXiv:2112.03376

Code (0)

등록된 구현이 없습니다.

Tasks

reinforcement-learningReinforcement Learning (RL)

Similar Papers 제목 키워드 기반

ε-BMC: A Bayesian Ensemble Approach to Epsilon-Greedy Exploration in Model-Free Reinforcement Learning

2020-07-02 · Michael Gimelfarb, Scott Sanner, Chi-Guhn Lee

Resolving the exploration-exploitation trade-off remains a fundamental problem in the design and implementation of reinforcement learning (RL) algorithms. In this paper, we focus on model-free RL using the epsilon-greedy…

Reinforcement Learning (RL)

Sample Complexity Bounds for Two Timescale Value-based Reinforcement Learning Algorithms

2020-11-10 · Tengyu Xu, Yingbin Liang

Two timescale stochastic approximation (SA) has been widely used in value-based reinforcement learning algorithms. In the policy evaluation setting, it can model the linear and nonlinear temporal difference learning with…

reinforcement-learningReinforcement Learning (RL)Vocal Bursts Valence Prediction

Faster Q-Learning Algorithms for Restless Bandits

2024-09-06 · Parvish Kakarapalli, Devendra Kayande, Rahul Meshram

We study the Whittle index learning algorithm for restless multi-armed bandits (RMAB). We first present Q-learning algorithm and its variants -- speedy Q-learning (SQL), generalized speedy Q-learning (GSQL) and phase Q-l…

Multi-Armed BanditsQ-Learning

On the Convergence and Sample Complexity Analysis of Deep Q-Networks with $\epsilon$-Greedy Exploration

2023-09-21 · NeurIPS 2023 11

This paper provides a theoretical understanding of deep Q-Network (DQN) with the $\varepsilon$-greedy exploration in deep reinforcement learning. Despite the tremendous empirical achievement of the DQN, its theoretical c…

On the Convergence and Sample Complexity Analysis of Deep Q-Networks with $ε$-Greedy Exploration

2023-10-24 · Shuai Zhang, Hongkang Li, Meng Wang, Miao Liu 외

This paper provides a theoretical understanding of Deep Q-Network (DQN) with the $\varepsilon$-greedy exploration in deep reinforcement learning. Despite the tremendous empirical achievement of the DQN, its theoretical c…

Deep Reinforcement LearningQ-Learning