Recruitment-imitation Mechanism for Evolutionary Reinforcement Learning

by   Shuai Lu, et al.

Reinforcement learning, evolutionary algorithms and imitation learning are three principal methods to deal with continuous control tasks. Reinforcement learning is sample efficient, yet sensitive to hyper-parameters setting and needs efficient exploration; Evolutionary algorithms are stable, but with low sample efficiency; Imitation learning is both sample efficient and stable, however it requires the guidance of expert data. In this paper, we propose Recruitment-imitation Mechanism (RIM) for evolutionary reinforcement learning, a scalable framework that combines advantages of the three methods mentioned above. The core of this framework is a dual-actors and single critic reinforcement learning agent. This agent can recruit high-fitness actors from the population of evolutionary algorithms, which instructs itself to learn from experience replay buffer. At the same time, low-fitness actors in the evolutionary population can imitate behavior patterns of the reinforcement learning agent and improve their adaptability. Reinforcement and imitation learners in this framework can be replaced with any off-policy actor-critic reinforcement learner or data-driven imitation learner. We evaluate RIM on a series of benchmarks for continuous control tasks in Mujoco. The experimental results show that RIM outperforms prior evolutionary or reinforcement learning methods. The performance of RIM's components is significantly better than components of previous evolutionary reinforcement learning algorithm, and the recruitment using soft update enables reinforcement learning agent to learn faster than that using hard update.


Episodic Self-Imitation Learning with Hindsight

Episodic self-imitation learning, a novel self-imitation algorithm with ...

Behavior-based Neuroevolutionary Training in Reinforcement Learning

In addition to their undisputed success in solving classical optimizatio...

Policy Supervectors: General Characterization of Agents by their Behaviour

By studying the underlying policies of decision-making agents, we can le...

Collaborative Evolutionary Reinforcement Learning

Deep reinforcement learning algorithms have been successfully applied to...

BiERL: A Meta Evolutionary Reinforcement Learning Framework via Bilevel Optimization

Evolutionary reinforcement learning (ERL) algorithms recently raise atte...

Delayed Reinforcement Learning by Imitation

When the agent's observations or interactions are delayed, classic reinf...

Please sign up or login with your details

Forgot password? Click here to reset