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 …
S Jordan, Y Chandak, D Cohen… - International …, 2020 - proceedings.mlr.press
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 …
RH Crites, AG Barto - Machine learning, 1998 - Springer
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 …