Abstract Safe Reinforcement Learning can be defined as the process of learning policies
that maximize the expectation of the return in problems in which it is important to ensure …

Multiagent Reinforcement Learning (RL) solves complex tasks that require coordination with
other agents through autonomous exploration of the environment. However, learning a …

We study worst-case guarantees on the expected return of fixed-dataset policy optimization
algorithms. Our core contribution is a unified conceptual and mathematical framework for the …

Providing Reinforcement Learning agents with expert advice can dramatically improve
various aspects of learning. Prior work has developed teaching protocols that enable agents …

Regularization is commonly used in classifier design, to assure good generalization.
Classical regularization enforces a cost on classifier complexity, by constraining parameters …

Methods to learn under algorithmic triage have predominantly focused on supervised
learning settings where each decision, or prediction, is independent of each other. Under …

Probabilistic planners have improved recently to the point that they can solve difficult tasks
with complex and expressive models. In contrast, learners cannot tackle yet the expressive …

Reinforcement learning agents have been mostly developed and evaluated under the
assumption that they will operate in a fully autonomous manner—they will take all actions. In …

We investigate the task of learning to follow natural language instructions by jointly
reasoning with visual observations and language inputs. In contrast to existing methods …

Learning to solve sequential decision-making tasks is difficult. Humans take years exploring
the environment essentially in a random way until they are able to reason, solve difficult …