Deep Reinforcement Learning using Genetic Algorithm for Parameter Optimization
arXiv:1905.04100
Abstract
Reinforcement learning (RL) enables agents to take decision based on a reward function. However, in the process of learning, the choice of values for learning algorithm parameters can significantly impact the overall learning process. In this paper, we use a genetic algorithm (GA) to find the values of parameters used in Deep Deterministic Policy Gradient (DDPG) combined with Hindsight Experience Replay (HER), to help speed up the learning agent. We used this method on fetch-reach, slide, push, pick and place, and door opening in robotic manipulation tasks. Our experimental evaluation shows that our method leads to better performance, faster than the original algorithm.
References in corpus (7)
- Continuous control with deep reinforcement learning
- Dueling Network Architectures for Deep Reinforcement Learning
- Evolutionary Algorithms for Reinforcement Learning
- Hindsight Experience Replay
- Cooperative and Distributed Reinforcement Learning of Drones for Field Coverage
- Autonomous UAV Navigation Using Reinforcement Learning
- Deep Learning with Experience Ranking Convolutional Neural Network for Robot Manipulator