We consider a general class of non-linear Bellman equations. These open ...
We consider the core reinforcement-learning problem of on-policy value
f...
It has been established that diverse behaviors spanning the controllable...
The ability to transfer skills across tasks has the potential to scale u...
The ability of a reinforcement learning (RL) agent to learn about many r...
Deep reinforcement learning (RL) algorithms have made great strides in r...
We propose Ephemeral Value Adjusments (EVA): a means of allowing deep
re...
Temporal-Difference learning (TD) [Sutton, 1988] with function approxima...
Some real-world domains are best characterized as a single task, but for...
One of the key challenges of artificial intelligence is to learn models ...
Transfer in reinforcement learning refers to the notion that generalizat...