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...
Inverse Reinforcement Learning (IRL) is the problem of learning the reward function underlying a Markov Decision Process given the dynamics of the system and the behaviour of an e...
We investigate the problem of non-covariant behavior of policy gradient reinforcement learning algorithms. The policy gradient approach is amenable to analysis by information geom...
Bayesian inference is an appealing approach for leveraging prior knowledge in reinforcement learning (RL). In this paper we describe an algorithm for discovering different classes...
As learning agents move from research labs to the real world, it is increasingly important that human users, including those without programming skills, be able to teach agents de...