Influence-aware memory architectures for deep reinforcement learning in POMDPs

Due to its perceptual limitations, an agent may have too little information about the environment to act optimally. In such cases, it is important to keep track of the action-observation history to uncover hidden state information. Recent deep reinforcement learning methods use recurrent neural networks (RNN) to memorize past observations....

Influence-Based Abstraction in Deep Reinforcement Learning

thousands, or even millions of state variables. Unfortunately, applying reinforcement learning algorithms to handle complex tasks becomes more and more challenging as the number of state variables increases. In this paper, we build on the concept of influence-based abstraction which tries to tackle such scalability issues by decomposing large...

Action Selection Policies for Walking Monte Carlo Tree Search

Recent Reinforcement Learning methods have combined function approximation and Monte Carlo Tree Search and are able to learn by self-play up to a very high level in several games such as Go and Hex. One aspect in this combination<br/>that has not had a lot of attention is the action selection policy during self-play, which could influence the...