Creating autonomous robots that can actively explore the environment, acquire knowledge
and learn skills continuously is the ultimate achievement envisioned in cognitive and …

Stochastic optimization is an umbrella term that includes over a dozen fragmented
communities, using a patchwork of sometimes overlapping notational systems with …

Noisy sensing, imperfect control, and environment changes are defining characteristics of
many real-world robot tasks. The partially observable Markov decision process (POMDP) …

In a standard view of the reinforcement learning problem, an agent's goal is to efficiently
identify a policy that maximizes long-term reward. However, this perspective is based on a …

Trading off exploration and exploitation in an unknown environment is key to maximising
expected return during learning. A Bayes-optimal policy, which does so optimally, conditions …

Many problems in RL, such as meta-RL, robust RL, generalization in RL, and temporal credit
assignment, can be cast as POMDPs. In theory, simply augmenting model-free RL with …

Consider the following instance of the Offline Meta Reinforcement Learning (OMRL)
problem: given the complete training logs of $ N $ conventional RL agents, trained on $ N …

This is the first rigorous, self-contained treatment of the theory of deep learning. Starting with
the foundations of the theory and building it up, this is essential reading for any scientists …

Learning a good representation is an essential component for deep reinforcement learning
(RL). Representation learning is especially important in multitask and partially observable …

This paper surveys the field of reinforcement learning from a computer-science perspective.
It is written to be accessible to researchers familiar with machine learning. Both the historical …