ACE: An Actor Ensemble Algorithm for Continuous Control with Tree Search
This work addresses continuous control tasks in robotics, offering a performance improvement over existing methods, though it appears incremental as it builds on DDPG and ensemble techniques.
The paper tackles the problem of continuous control in reinforcement learning by proposing ACE, an actor ensemble algorithm combined with tree search, which significantly outperforms DDPG and its variants in challenging physical robot simulators.
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.