Importance Sampling based Exploration in Q Learning

Abstract

Approximate Dynamic Programming (ADP) is a methodology to solve multi-stage stochastic optimization problems in multi-dimensional discrete or continuous spaces. ADP approximates the optimal value function by adaptively sampling both action and state space. It provides a tractable approach to very large problems, but can suffer from the exploration-exploitation dilemma. We propose a novel approach for selecting actions using importance sampling weighted by the value function approximation in continuous decision spaces to address this dilemma. An advantage of this approach is it balances exploration and exploitation without any tuning parameters when sampling actions compared to other exploration approaches such as Epsilon Greedy, instead relying only on the approximate value function. We compare the proposed algorithm with other exploration strategies in continuous action space in the context of a multi-stage generation expansion planning problem under uncertainty.

References in corpus (11)

• Continuous control with deep reinforcement learning
• Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor
• QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulation
• Count-Based Exploration with Neural Density Models
• #Exploration: A Study of Count-Based Exploration for Deep Reinforcement Learning
• Continuous Deep Q-Learning with Model-based Acceleration
• Input Convex Neural Networks
• Using Options and Covariance Testing for Long Horizon Off-Policy Policy Evaluation
• Multi-step Off-policy Learning Without Importance Sampling Ratios
• Q-Learning for Continuous Actions with Cross-Entropy Guided Policies
• CAQL: Continuous Action Q-Learning