Improving Actor-Critic Reinforcement Learning via Hamiltonian Policy
Approximating optimal policies in reinforcement learning (RL) is often necessary in many real-world scenarios, which is termed as policy optimization. By viewing the reinforcement learning from the perspective of variational inference (VI), the policy network is trained to obtain the approximate posterior of actions given the optimality criteria. However, in practice, the policy optimization may lead to suboptimal policy estimates due to the amortization gap and insufficient exploration. In this work, inspired by the previous use of Hamiltonian Monte Carlo (HMC) in VI, we propose to integrate policy optimization with HMC. As such we choose evolving actions from the base policy according to HMC, which has two benefits: i) HMC can improve the policy distribution to better approximate the posterior and hence reduces the amortization gap; ii) HMC can also guide the exploration more to the regions with higher action values, enhancing the exploration efficiency. Instead of directly applying HMC into RL, we propose a new leapfrog operator to simulate the Hamiltonian dynamics. With comprehensive empirical experiments on continuous control baselines, including MuJoCo and PyBullet Roboschool, we show that the proposed approach is a data-efficient, and an easy-to-implement improvement over previous policy optimization methods. Besides, the proposed approach can also outperform previous methods on DeepMind Control Suite which has image-based high-dimensional observation space.
READ FULL TEXT