Abstract. Innovations such as optimistic exploration, function approximation, and hierarchical decomposition have helped scale reinforcement learning to more complex environments, ...
This paper is concerned with how multi-agent reinforcement learning algorithms can practically be applied to real-life problems. Recently, a new coordinated multi-agent exploratio...
Many robot control problems of practical importance, including operational space control, can be reformulated as immediate reward reinforcement learning problems. However, few of ...
We generalise the problem of inverse reinforcement learning to multiple tasks, from multiple demonstrations. Each one may represent one expert trying to solve a different task, or ...
This paper describes the adaption and application of an algorithm called Feudal Reinforcement Learning to a complex gridworld navigation problem. The algorithm proved to be not ea...