Evolutionary Reinforcement Learning via Cooperative Coevolutionary Negatively Correlated Search

by   Hu Zhang, et al.

Evolutionary algorithms (EAs) have been successfully applied to optimize the policies for Reinforcement Learning (RL) tasks due to their exploration ability. The recently proposed Negatively Correlated Search (NCS) provides a distinct parallel exploration search behavior and is expected to facilitate RL more effectively. Considering that the commonly adopted neural policies usually involves millions of parameters to be optimized, the direct application of NCS to RL may face a great challenge of the large-scale search space. To address this issue, this paper presents an NCS-friendly Cooperative Coevolution (CC) framework to scale-up NCS while largely preserving its parallel exploration search behavior. The issue of traditional CC that can deteriorate NCS is also discussed. Empirical studies on 10 popular Atari games show that the proposed method can significantly outperform three state-of-the-art deep RL methods with 50 search space.


page 1

page 2

page 3

page 4


Reinforcement Learning with Chromatic Networks

We present a new algorithm for finding compact neural networks encoding ...

Deep Reinforcement Learning with Smooth Policy

Deep neural networks have been widely adopted in modern reinforcement le...

Negatively Correlated Search as a Parallel Exploration Search Strategy

Parallel exploration is a key to a successful search. The recently propo...

Learning Large Neighborhood Search Policy for Integer Programming

We propose a deep reinforcement learning (RL) method to learn large neig...

Evolutionary Reinforcement Learning

Deep Reinforcement Learning (DRL) algorithms have been successfully appl...

RADARS: Memory Efficient Reinforcement Learning Aided Differentiable Neural Architecture Search

Differentiable neural architecture search (DNAS) is known for its capaci...

Hybridization of Interval CP and Evolutionary Algorithms for Optimizing Difficult Problems

The only rigorous approaches for achieving a numerical proof of optimali...