Despite the seeming success of contemporary grounded text generation sys...
Traditionally, Reinforcement Learning (RL) aims at deciding how to act
o...
Incorporating prior knowledge in reinforcement learning algorithms is ma...
We propose to learn to distinguish reversible from irreversible actions ...
Despite definite success in deep reinforcement learning problems,
actor-...
Self-imitation learning is a Reinforcement Learning (RL) method that
enc...
The ability to transfer representations to novel environments and tasks ...