V-MPO: On-Policy Maximum a Posteriori Policy Optimization for Discrete and Continuous Control
This work addresses performance and reliability issues in reinforcement learning for discrete and continuous control, offering a method that eliminates the need for entropy regularization and hyperparameter tuning, though it is incremental as it builds on existing MPO approaches.
The paper tackles the challenge of policy gradient methods in deep reinforcement learning, which suffer from high variance and require careful tuning, by introducing V-MPO, an on-policy adaptation of Maximum a Posteriori Policy Optimization that surpasses previous scores on Atari-57 and DMLab-30 benchmarks and achieves higher asymptotic scores on continuous control tasks.
Some of the most successful applications of deep reinforcement learning to challenging domains in discrete and continuous control have used policy gradient methods in the on-policy setting. However, policy gradients can suffer from large variance that may limit performance, and in practice require carefully tuned entropy regularization to prevent policy collapse. As an alternative to policy gradient algorithms, we introduce V-MPO, an on-policy adaptation of Maximum a Posteriori Policy Optimization (MPO) that performs policy iteration based on a learned state-value function. We show that V-MPO surpasses previously reported scores for both the Atari-57 and DMLab-30 benchmark suites in the multi-task setting, and does so reliably without importance weighting, entropy regularization, or population-based tuning of hyperparameters. On individual DMLab and Atari levels, the proposed algorithm can achieve scores that are substantially higher than has previously been reported. V-MPO is also applicable to problems with high-dimensional, continuous action spaces, which we demonstrate in the context of learning to control simulated humanoids with 22 degrees of freedom from full state observations and 56 degrees of freedom from pixel observations, as well as example OpenAI Gym tasks where V-MPO achieves substantially higher asymptotic scores than previously reported.