Partially Observable Markov Decision Processes (POMDPs) have succeeded in planning domains that require balancing actions that increase an agent's knowledge and actions that ...
Reinforcement Learning is a commonly used technique in robotics, however, traditional algorithms are unable to handle large amounts of data coming from the robot’s sensors, requi...
We present an expressive agent design language for reinforcement learning that allows the user to constrain the policies considered by the learning process.The language includes s...
In this paper we study the topic of CBR systems learning from observations in which those observations can be represented as stochastic policies. We describe a general framework wh...
Kellen Gillespie, Justin Karneeb, Stephen Lee-Urba...
We cast model-free reinforcement learning as the problem of maximizing the likelihood of a probabilistic mixture model via sampling, addressing both the infinite and finite horizo...