Posterior Sampling for Deep Reinforcement Learning
This addresses sample inefficiency for reinforcement learning practitioners, offering a scalable solution with concrete performance gains.
The paper tackles the sample inefficiency problem in deep reinforcement learning by introducing PSDRL, a scalable model-based algorithm that combines uncertainty quantification with continual planning. Experiments on Atari show it outperforms previous posterior sampling methods and is competitive with state-of-the-art model-based approaches in sample and computational efficiency.
Despite remarkable successes, deep reinforcement learning algorithms remain sample inefficient: they require an enormous amount of trial and error to find good policies. Model-based algorithms promise sample efficiency by building an environment model that can be used for planning. Posterior Sampling for Reinforcement Learning is such a model-based algorithm that has attracted significant interest due to its performance in the tabular setting. This paper introduces Posterior Sampling for Deep Reinforcement Learning (PSDRL), the first truly scalable approximation of Posterior Sampling for Reinforcement Learning that retains its model-based essence. PSDRL combines efficient uncertainty quantification over latent state space models with a specially tailored continual planning algorithm based on value-function approximation. Extensive experiments on the Atari benchmark show that PSDRL significantly outperforms previous state-of-the-art attempts at scaling up posterior sampling while being competitive with a state-of-the-art (model-based) reinforcement learning method, both in sample efficiency and computational efficiency.