Convergence Guarantees for Deep Epsilon Greedy Policy Learning
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.
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
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
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 PredictionFaster Q-Learning Algorithms for Restless Bandits
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-LearningOn the Convergence and Sample Complexity Analysis of Deep Q-Networks with $\epsilon$-Greedy Exploration
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
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