1 citations · 1 across the 5 of their papers we have counts for
3 papers · 1 filter
On the Interplay Between Sparsity and Training in Deep Reinforcement Learning
Fatima Davelouis, John D. Martin, Michael Bowling
We study the benefits of different sparse architectures for deep reinforcement learning. In particular, we focus on image-based domains where spatially-biased and fully-connected a…
Meta-Gradient Search Control: A Method for Improving the Efficiency of Dyna-style Planning
Bradley Burega, John D. Martin, Luke Kapeluck +1
We study how a Reinforcement Learning (RL) system can remain sample-efficient when learning from an imperfect model of the environment. This is particularly challenging when the le…
MOTO: Offline Pre-training to Online Fine-tuning for Model-based Robot Learning
Rafael Rafailov, Kyle Hatch, Victor Kolev +3
We study the problem of offline pre-training and online fine-tuning for reinforcement learning from high-dimensional observations in the context of realistic robot tasks. Recent of…