A key challenge in intelligent robotics is creating robots that are capable of directly
interacting with the world around them to achieve their goals. The last decade has seen …

A generally intelligent agent faces a dilemma: it requires a complex sensorimotor space to
be capable of solving a wide range of problems, but many tasks are only feasible given the …

We study the sample complexity of model-based reinforcement learning (henceforth RL) in
general contextual decision processes that require strategic exploration to find a near …

This book is written for students and researchers in the field of industrial engineering,
computer science, operations research, management science, electrical engineering, and …

We study the problem of learning near-optimal behavior in finite Markov Decision Processes
(MDPs) with a polynomial number of samples. These “PAC-MDP” algorithms include the …

We introduce a learning framework that combines elements of the well-known PAC and
mistake-bound models. The KWIK (knows what it knows) framework was designed …

In real-world reinforcement learning applications the learner's observation space is
ubiquitously high-dimensional with both relevant and irrelevant information about the task at …

The use of robots in society could be expanded by using reinforcement learning (RL) to
allow robots to learn and adapt to new situations online. RL is a paradigm for learning …

Transferring knowledge across a sequence of reinforcement-learning tasks is challenging,
and has a number of important applications. Though there is encouraging empirical …

We consider the problem of learning action models for planning in unknown stochastic
environments that can be defined using the Probabilistic Planning Domain Description …