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...
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...
A key component of any reinforcement learning algorithm is the underlying representation used by the agent. While reinforcement learning (RL) agents have typically relied on hand-...
Improving the sample efficiency of reinforcement learning algorithms to scale up to larger and more realistic domains is a current research challenge in machine learning. Model-ba...
ion mechanism to create a representation of space consisting of the circular order of detected landmarks and the relative position of walls towards the agent's moving directio...