André Barreto

Fast deep reinforcement learning using online adjustments from the past

2018 · arXiv (Cornell University)

We propose Ephemeral Value Adjusments (EVA): a means of allowing deep reinforcement learning agents to rapidly adapt to experience in their replay buffer. EVA shifts the value predicted by a neural network with an estimate …

Discovering Diverse Nearly Optimal Policies withSuccessor Features.

2021 · arXiv (Cornell University)

Finding different solutions to the same problem is a key aspect of intelligence associated with creativity and adaptation to novel situations. In reinforcement learning, a set of diverse policies can be useful for exploration, transfer, …