5 citations · 12 across the 4 of their papers we have counts for
3 papers · 1 filter
Safe Policy Improvement Approaches and their Limitations
Philipp Scholl, Felix Dietrich, Clemens Otte +1
Safe Policy Improvement (SPI) is an important technique for offline reinforcement learning in safety critical applications as it improves the behavior policy with a high probabilit…
Safe Policy Improvement Approaches on Discrete Markov Decision Processes
Philipp Scholl, Felix Dietrich, Clemens Otte +1
Safe Policy Improvement (SPI) aims at provable guarantees that a learned policy is at least approximately as good as a given baseline policy. Building on SPI with Soft Baseline Boo…
Interpretable Dynamics Models for Data-Efficient Reinforcement Learning
Markus Kaiser, Clemens Otte, Thomas Runkler +1
In this paper, we present a Bayesian view on model-based reinforcement learning. We use expert knowledge to impose structure on the transition model and present an efficient learni…