GA+DDPG+HER: Genetic Algorithm-Based Function Optimizer in Deep Reinforcement Learning for Robotic Manipulation Tasks

TL;DR

This paper introduces GA+DDPG+HER, a genetic algorithm-enhanced reinforcement learning method that automates parameter tuning, significantly improving learning speed and performance in robotic manipulation tasks.

Contribution

The study extends previous work by integrating genetic algorithms with DDPG and HER to optimize parameters automatically for better RL performance.

Findings

Performance improved over original algorithms

Learning time reduced by up to 57%

Outperforms current state-of-the-art approaches

Abstract

Agents can base decisions made using reinforcement learning (RL) on a reward function. The selection of values for the learning algorithm parameters can, nevertheless, have a substantial impact on the overall learning process. In order to discover values for the learning parameters that are close to optimal, we extended our previously proposed genetic algorithm-based Deep Deterministic Policy Gradient and Hindsight Experience Replay approach (referred to as GA+DDPG+HER) in this study. On the robotic manipulation tasks of FetchReach, FetchSlide, FetchPush, FetchPick&Place, and DoorOpening, we applied the GA+DDPG+HER methodology. Our technique GA+DDPG+HER was also used in the AuboReach environment with a few adjustments. Our experimental analysis demonstrates that our method produces performance that is noticeably better and occurs faster than the original algorithm. We also offer proof that GA+DDPG+HER beat the current approaches. The final results support our assertion and offer sufficient proof that automating the parameter tuning procedure is crucial and does cut down learning time by as much as 57%.