Reinforcement learning (RL) algorithms find applications in inventory control, recommender
systems, vehicular traffic management, cloud computing, and robotics. The real-world …

Reinforcement learning (RL) methods learn optimal decisions in the presence of a stationary
environment. However, the stationary assumption on the environment is very restrictive. In …

Reinforcement learning (RL) has proven its worth in a series of artificial domains, and is
beginning to show some successes in real-world scenarios. However, much of the research …

Exploration is a key problem in reinforcement learning, since agents can only learn from
data they acquire in the environment. With that in mind, maintaining a population of agents is …

Performance evaluations are critical for quantifying algorithmic advances in reinforcement
learning. Recent reproducibility analyses have shown that reported performance results are …

Reinforcement learning (RL) has proven its worth in a series of artificial domains, and is
beginning to show some successes in real-world scenarios. However, much of the research …

Recent algorithmic and theoretical advances in reinforcement learning (RL) have attracted
widespread interest. RL algorithms have appeared that approximate dynamic programming …

We present a framework for reinforcement learning (RL) in a scenario where multiple
simulators are available with decreasing amounts of fidelity to the real-world learning …

This dissertation is about building learning control architectures for agents embedded in
finite, stationary, and Markovian environments. Such architectures give embedded agents …

Reinforcement learning (RL) has proven its worth in a series of artificial domains, and is
beginning to show some successes in real-world scenarios. However, much of the research …