Deep Reinforcement Learning using Genetic Algorithm for Parameter Optimization
This work addresses parameter tuning challenges for researchers and practitioners in robotics, but it is incremental as it combines existing methods without introducing a fundamentally new approach.
The paper tackles the problem of parameter selection in deep reinforcement learning by using a genetic algorithm to optimize parameters for DDPG combined with HER, resulting in improved performance and faster learning in robotic manipulation tasks.
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.