Adaptive and Multiple Time-scale Eligibility Traces for Online Deep Reinforcement Learning

TL;DR

This paper introduces an adaptive, multi-time-scale eligibility traces method for online deep reinforcement learning, enhancing sample efficiency and adaptability in environments with changing dynamics.

Contribution

It proposes a novel eligibility traces technique compatible with deep neural networks, incorporating divergence-based adaptive decay and multiple time-scale traces for improved online learning.

Findings

Enhanced sample efficiency in DRL tasks

Effective handling of environment changes

Compatibility with deep neural network training

Abstract

Deep reinforcement learning (DRL) is one promising approach to teaching robots to perform complex tasks. Because methods that directly reuse the stored experience data cannot follow the change of the environment in robotic problems with a time-varying environment, online DRL is required. The eligibility traces method is well known as an online learning technique for improving sample efficiency in traditional reinforcement learning with linear regressors rather than DRL. The dependency between parameters of deep neural networks would destroy the eligibility traces, which is why they are not integrated with DRL. Although replacing the gradient with the most influential one rather than accumulating the gradients as the eligibility traces can alleviate this problem, the replacing operation reduces the number of reuses of previous experiences. To address these issues, this study proposes a new eligibility traces method that can be used even in DRL while maintaining high sample efficiency. When the accumulated gradients differ from those computed using the latest parameters, the proposed method takes into account the divergence between the past and latest parameters to adaptively decay the eligibility traces. Bregman divergences between outputs computed by the past and latest parameters are exploited due to the infeasible computational cost of the divergence between the past and latest parameters. In addition, a generalized method with multiple time-scale traces is designed for the first time. This design allows for the replacement of the most influential adaptively accumulated (decayed) eligibility traces.