These have the opposite properties, with DRL having good sample efficiencyandpoor stability, while ESbeing vice versa. Recently,there havebeen attempts tocombine these algorithms, butthesemethods fullyrelyonsynchronous updatescheme, making it not ideal to maximize the benefits of the parallelism in ES.

We thank the reviewers for the reviews, providing meaningful insight with constructive feedback. The result was reversed in Hopper, where RL contributed 200.86 while EA actors did 363.53. Therefore, all performance result scores are measured in the fixed interaction step. R2: Ablation study is missing. We presented the effect of the variance update rule in Appendix C.3 by comparing the result Then, we provided all combinations of our proposed mean and variance in Table 2. We will add a section so that it can be seen at a glance.

These have the opposite properties, with DRL having good sample efficiency and poor stability, while ES being vice versa.

Evolutionary Algorithms and Deep Reinforcement Learning have both successfully solved control problems across a variety of domains. Recently, algorithms have been proposed which combine these two methods, aiming to leverage the strengths and mitigate the weaknesses of both approaches. In this paper we introduce a new Evolutionary Reinforcement Learning model which combines a particular family of Evolutionary algorithm called Evolutionary Strategies with the off-policy Deep Reinforcement Learning algorithm TD3. The framework utilises a multi-buffer system instead of using a single shared replay buffer. The multi-buffer system allows for the Evolutionary Strategy to search freely in the search space of policies, without running the risk of overpopulating the replay buffer with poorly performing trajectories which limit the number of desirable policy behaviour examples thus negatively impacting the potential of the Deep Reinforcement Learning within the shared framework. The proposed algorithm is demonstrated to perform competitively with current Evolutionary Reinforcement Learning algorithms on MuJoCo control tasks, outperforming the well known state-of-the-art CEM-RL on 3 of the 4 environments tested.

Deep reinforcement learning (DRL) algorithms and evolution strategies (ES) have been applied to various tasks, showing excellent performances. These have the opposite properties, with DRL having good sample efficiency and poor stability, while ES being vice versa. Recently, there have been attempts to combine these algorithms, but these methods fully rely on synchronous update scheme, making it not ideal to maximize the benefits of the parallelism in ES. To solve this challenge, asynchronous update scheme was introduced, which is capable of good time-efficiency and diverse policy exploration. In this paper, we introduce an Asynchronous Evolution Strategy-Reinforcement Learning (AES-RL) that maximizes the parallel efficiency of ES and integrates it with policy gradient methods. Specifically, we propose 1) a novel framework to merge ES and DRL asynchronously and 2) various asynchronous update methods that can take all advantages of asynchronism, ES, and DRL, which are exploration and time efficiency, stability, and sample efficiency, respectively. The proposed framework and update methods are evaluated in continuous control benchmark work, showing superior performance as well as time efficiency compared to the previous methods.