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...
Appropriately designing sampling policies is highly important for obtaining better control policies in reinforcement learning. In this paper, we first show that the least-squares ...
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...
— Reinforcement learning (RL) algorithms have long been promising methods for enabling an autonomous robot to improve its behavior on sequential decision-making tasks. The obviou...
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...