The reward hypothesis posits that, "all of what we mean by goals and pur...
Reinforcement learning defines the problem facing agents that learn to m...
Reward is the driving force for reinforcement-learning agents. This pape...
Reinforcement learning is hard in general. Yet, in many specific
environ...
One of the most striking features of human cognition is the capacity to ...
Off-policy multi-step reinforcement learning algorithms consist of
conse...
Reinforcement learning algorithms usually assume that all actions are al...
Planning is useful. It lets people take actions that have desirable long...
Can simple algorithms with a good representation solve challenging
reinf...
We consider the problem of knowledge transfer when an agent is facing a
...
One of the main challenges in reinforcement learning is solving tasks wi...
An agent with an inaccurate model of its environment faces a difficult
c...
While adding temporally abstract actions, or options, to an agent's acti...
Deep neural networks are able to solve tasks across a variety of domains...
The combinatorial explosion that plagues planning and reinforcement lear...
Providing Reinforcement Learning agents with expert advice can dramatica...
High-dimensional observations and complex real-world dynamics present ma...