Showing cs.LGShow all
2 papers · 1 filter
cs.LG2021
Reward prediction for representation learning and reward shaping
Hlynur Davíð Hlynsson, Laurenz Wiskott
One of the fundamental challenges in reinforcement learning (RL) is the one of data efficiency: modern algorithms require a very large number of training samples, especially compar…
cs.LG2020
Latent Representation Prediction Networks
Hlynur Davíð Hlynsson, Merlin Schüler, Robin Schiewer +2
Deeply-learned planning methods are often based on learning representations that are optimized for unrelated tasks. For example, they might be trained on reconstructing the environ…