Showing 2024Show all
3 papers · 1 filter
cs.LG2024
MAD-TD: Model-Augmented Data stabilizes High Update Ratio RL
Claas A Voelcker, Marcel Hussing, Eric Eaton +2
Building deep reinforcement learning (RL) agents that find a good policy with few samples has proven notoriously challenging. To achieve sample efficiency, recent work has explored…
cs.LG2024
When does Self-Prediction help? Understanding Auxiliary Tasks in Reinforcement Learning
Claas Voelcker, Tyler Kastner, Igor Gilitschenski +1
We investigate the impact of auxiliary learning tasks such as observation reconstruction and latent self-prediction on the representation learning problem in reinforcement learning…
cs.LG2024
Dissecting Deep RL with High Update Ratios: Combatting Value Divergence
Marcel Hussing, Claas Voelcker, Igor Gilitschenski +2
We show that deep reinforcement learning algorithms can retain their ability to learn without resetting network parameters in settings where the number of gradient updates greatly…