Showing cs.LGShow all
2 papers · 1 filter
cs.LG2025
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…
cs.LG2024
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…