Comparing Deep Reinforcement Learning and Evolutionary Methods in Continuous Control
This work addresses the choice of optimization methods for researchers and practitioners in robotics and control, but it is incremental as it compares existing techniques without introducing new ones.
The paper compared deep reinforcement learning and evolutionary methods for continuous control tasks, finding no consistent winner between the two approaches.
Reinforcement Learning and the Evolutionary Strategy are two major approaches in addressing complicated control problems. Both are strong contenders and have their own devotee communities. Both groups have been very active in developing new advances in their own domain and devising, in recent years, leading-edge techniques to address complex continuous control tasks. Here, in the context of Deep Reinforcement Learning, we formulate a parallelized version of the Proximal Policy Optimization method and a Deep Deterministic Policy Gradient method. Moreover, we conduct a thorough comparison between the state-of-the-art techniques in both camps fro continuous control; evolutionary methods and Deep Reinforcement Learning methods. The results show there is no consistent winner.