AIConfPaper
← Search

Sarah Bechtle

4 accepted papers

2024

Mastering Stacking of Diverse Shapes with Large-Scale Iterative Reinforcement Learning on Real Robots

Thomas Lampe, Abbas Abdolmaleki, Sarah Bechtle, Sandy H. Huang, Jost Tobias Springenberg, Michael Bloesch +9
ICRA 2024poster

Reinforcement learning solely from an agent’s self-generated data is often believed to be infeasible for learning on real robots, due to the amount of data needed. However, if done right, agents learning from real data can be surprisingly efficient through re-using previously collected sub-optimal d…

Cited by 6Source ↗Scholar ↗
2021

Leveraging Forward Model Prediction Error for Learning Control

Sarah Bechtle, Bilal Hammoud, Akshara Rai, Franziska Meier, Ludovic Righetti
ICRA 2021poster

Learning for model based control can be sample-efficient and generalize well, however successfully learning models and controllers that represent the problem at hand can be challenging for complex tasks. Using inaccurate models for learning can lead to sub-optimal solutions that are unlikely to perf…

Cited by 5Source ↗Scholar ↗
2020

Model-Based Inverse Reinforcement Learning from Visual Demonstrations

Neha Das, Sarah Bechtle, Todor Davchev, Dinesh Jayaraman, Akshara Rai, Franziska Meier
CoRL 2020

Scaling model-based inverse reinforcement learning (IRL) to real robotic manipulation tasks with unknown dynamics remains an open problem. The key challenges lie in learning good dynamics models, developing algorithms that scale to high-dimensional state-spaces and being able to learn from both visu

Cited by 0Source ↗PDF ↗Scholar ↗
2019

Curious iLQR: Resolving Uncertainty in Model-based RL

Sarah Bechtle, Yixin Lin, Akshara Rai, Ludovic Righetti, Franziska Meier
CoRL 2019

Curiosity as a means to explore during reinforcement learning problems has recently become very popular. However, very little progress has been made in utilizing curiosity for learning control. In this work, we propose a model-based reinforcement learning (MBRL) framework that combines Bayesian mode

Cited by 0Source ↗PDF ↗Scholar ↗