Optimistic Reinforcement Learning by Forward Kullback-Leibler Divergence Optimization

Abstract

This paper addresses a new interpretation of the traditional optimization method in reinforcement learning (RL) as optimization problems using reverse Kullback-Leibler (KL) divergence, and derives a new optimization method using forward KL divergence, instead of reverse KL divergence in the optimization problems. Although RL originally aims to maximize return indirectly through optimization of policy, the recent work by Levine has proposed a different derivation process with explicit consideration of optimality as stochastic variable. This paper follows this concept and formulates the traditional learning laws for both value function and policy as the optimization problems with reverse KL divergence including optimality. Focusing on the asymmetry of KL divergence, the new optimization problems with forward KL divergence are derived. Remarkably, such new optimization problems can be regarded as optimistic RL. That optimism is intuitively specified by a hyperparameter converted from an uncertainty parameter. In addition, it can be enhanced when it is integrated with prioritized experience replay and eligibility traces, both of which accelerate learning. The effects of this expected optimism was investigated through learning tendencies on numerical simulations using Pybullet. As a result, moderate optimism accelerated learning and yielded higher rewards. In a realistic robotic simulation, the proposed method with the moderate optimism outperformed one of the state-of-the-art RL method.

arXiv comment14 pages, 6 figures

References in corpus (22)

• Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor
• Trust Region Policy Optimization
• Addressing Function Approximation Error in Actor-Critic Methods
• Prioritized Experience Replay
• High-Dimensional Continuous Control Using Generalized Advantage Estimation
• OpenAI Gym
• Reinforcement Learning and Control as Probabilistic Inference: Tutorial and Review
• Deep Reinforcement Learning that Matters
• Self-Imitation Learning
• Safe and Efficient Off-Policy Reinforcement Learning
• t-Soft Update of Target Network for Deep Reinforcement Learning
• How Many Random Seeds? Statistical Power Analysis in Deep Reinforcement Learning Experiments
• Model-Augmented Actor-Critic: Backpropagating through Paths
• Variational Inference MPC for Bayesian Model-based Reinforcement Learning
• Imitation Learning as $f$-Divergence Minimization
• Domain-Independent Optimistic Initialization for Reinforcement Learning
• Optimistic Exploration even with a Pessimistic Initialisation
• Effective Multi-step Temporal-Difference Learning for Non-Linear Function Approximation
• Adaptive and Multiple Time-scale Eligibility Traces for Online Deep Reinforcement Learning
• Proximal Policy Optimization with Relative Pearson Divergence
• Uncertainty-aware Model-based Policy Optimization
• Soft Policy Gradient Method for Maximum Entropy Deep Reinforcement Learning

Cited by in corpus (6)

• Reward Bonuses with Gain Scheduling Inspired by Iterative Deepening Search
• Optimization Algorithm for Feedback and Feedforward Policies towards Robot Control Robust to Sensing Failures
• Consolidated Adaptive T-soft Update for Deep Reinforcement Learning
• Revisiting Experience Replayable Conditions
• A unified framework for divergences, free energies, and Fokker-Planck equations
• Weber-Fechner Law in Temporal Difference learning derived from Control as Inference