← Search

Trimpe Sebastian

2 accepted papers

2019

Trajectory-Based Off-Policy Deep Reinforcement Learning

ICML 2019oral

Policy gradient methods are powerful reinforcement learning algorithms and have been demonstrated to solve many complex tasks. However, these methods are also data-inefficient, afflicted with high variance gradient estimates, and frequently get stuck in local optima. This work addresses these weakne…

2018

Probabilistic Recurrent State-Space Models

ICML 2018oral

State-space models (SSMs) are a highly expressive model class for learning patterns in time series data and for system identification. Deterministic versions of SSMs (e.g., LSTMs) proved extremely successful in modeling complex time series data. Fully probabilistic SSMs, however, are often found har…