ACE: An Actor Ensemble Algorithm for Continuous Control with Tree Search

Abstract

In this paper, we propose an actor ensemble algorithm, named ACE, for continuous control with a deterministic policy in reinforcement learning. In ACE, we use actor ensemble (i.e., multiple actors) to search the global maxima of the critic. Besides the ensemble perspective, we also formulate ACE in the option framework by extending the option-critic architecture with deterministic intra-option policies, revealing a relationship between ensemble and options. Furthermore, we perform a look-ahead tree search with those actors and a learned value prediction model, resulting in a refined value estimation. We demonstrate a significant performance boost of ACE over DDPG and its variants in challenging physical robot simulators.

AAAI 2019

References in corpus (6)

• DeepMind Control Suite
• Deep Exploration via Bootstrapped DQN
• Distributed Distributional Deterministic Policy Gradients
• Value Prediction Network
• Learnings Options End-to-End for Continuous Action Tasks
• Learning to Run with Actor-Critic Ensemble