In this theoretical contribution we provide mathematical proof that two of the most important classes of network learning - correlation-based differential Hebbian learning and rew...
Christoph Kolodziejski, Bernd Porr, Minija Tamosiu...
Reinforcement learning addresses the problem of learning to select actions in order to maximize one's performance inunknownenvironments. Toscale reinforcement learning to com...
The aim of transfer learning is to accelerate learning in related domains. In reinforcement learning, many different features such as a value function and a policy can be transfer...
Transfer learning problems are typically framed as leveraging knowledge learned on a source task to improve learning on a related, but different, target task. Current transfer met...
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...