Philip Ball

Stabilizing Off-Policy Deep Reinforcement Learning from Pixels

2022 · arXiv (Cornell University)

Off-policy reinforcement learning (RL) from pixel observations is notoriously unstable. As a result, many successful algorithms must combine different domain-specific practices and auxiliary losses to learn meaningful behaviors in complex environments. In this work, we …

D5RL: Diverse Datasets for Data-Driven Deep Reinforcement Learning

2024 · arXiv (Cornell University)

Offline reinforcement learning algorithms hold the promise of enabling data-driven RL methods that do not require costly or dangerous real-world exploration and benefit from large pre-collected datasets. This in turn can facilitate real-world applications, as …