Header logo is


2017


On the Design of {LQR} Kernels for Efficient Controller Learning
On the Design of LQR Kernels for Efficient Controller Learning

Marco, A., Hennig, P., Schaal, S., Trimpe, S.

Proceedings of the 56th IEEE Annual Conference on Decision and Control (CDC), pages: 5193-5200, IEEE, IEEE Conference on Decision and Control, December 2017 (conference)

Abstract
Finding optimal feedback controllers for nonlinear dynamic systems from data is hard. Recently, Bayesian optimization (BO) has been proposed as a powerful framework for direct controller tuning from experimental trials. For selecting the next query point and finding the global optimum, BO relies on a probabilistic description of the latent objective function, typically a Gaussian process (GP). As is shown herein, GPs with a common kernel choice can, however, lead to poor learning outcomes on standard quadratic control problems. For a first-order system, we construct two kernels that specifically leverage the structure of the well-known Linear Quadratic Regulator (LQR), yet retain the flexibility of Bayesian nonparametric learning. Simulations of uncertain linear and nonlinear systems demonstrate that the LQR kernels yield superior learning performance.

am ics pn

arXiv PDF On the Design of LQR Kernels for Efficient Controller Learning - CDC presentation DOI Project Page [BibTex]

2017


arXiv PDF On the Design of LQR Kernels for Efficient Controller Learning - CDC presentation DOI Project Page [BibTex]


no image
Optimal gamification can help people procrastinate less

Lieder, F., Griffiths, T. L.

Annual Meeting of the Society for Judgment and Decision Making, Annual Meeting of the Society for Judgment and Decision Making, November 2017 (conference)

re

Project Page [BibTex]

Project Page [BibTex]


Optimizing Long-term Predictions for Model-based Policy Search
Optimizing Long-term Predictions for Model-based Policy Search

Doerr, A., Daniel, C., Nguyen-Tuong, D., Marco, A., Schaal, S., Toussaint, M., Trimpe, S.

Proceedings of 1st Annual Conference on Robot Learning (CoRL), 78, pages: 227-238, (Editors: Sergey Levine and Vincent Vanhoucke and Ken Goldberg), 1st Annual Conference on Robot Learning, November 2017 (conference)

Abstract
We propose a novel long-term optimization criterion to improve the robustness of model-based reinforcement learning in real-world scenarios. Learning a dynamics model to derive a solution promises much greater data-efficiency and reusability compared to model-free alternatives. In practice, however, modelbased RL suffers from various imperfections such as noisy input and output data, delays and unmeasured (latent) states. To achieve higher resilience against such effects, we propose to optimize a generative long-term prediction model directly with respect to the likelihood of observed trajectories as opposed to the common approach of optimizing a dynamics model for one-step-ahead predictions. We evaluate the proposed method on several artificial and real-world benchmark problems and compare it to PILCO, a model-based RL framework, in experiments on a manipulation robot. The results show that the proposed method is competitive compared to state-of-the-art model learning methods. In contrast to these more involved models, our model can directly be employed for policy search and outperforms a baseline method in the robot experiment.

am ics

PDF Project Page [BibTex]

PDF Project Page [BibTex]


Model-Based Policy Search for Automatic Tuning of Multivariate PID Controllers
Model-Based Policy Search for Automatic Tuning of Multivariate PID Controllers

Doerr, A., Nguyen-Tuong, D., Marco, A., Schaal, S., Trimpe, S.

In Proceedings of the IEEE International Conference on Robotics and Automation (ICRA), pages: 5295-5301, IEEE, Piscataway, NJ, USA, IEEE International Conference on Robotics and Automation (ICRA), May 2017 (inproceedings)

am ics

PDF arXiv DOI Project Page [BibTex]

PDF arXiv DOI Project Page [BibTex]


Virtual vs. {R}eal: Trading Off Simulations and Physical Experiments in Reinforcement Learning with {B}ayesian Optimization
Virtual vs. Real: Trading Off Simulations and Physical Experiments in Reinforcement Learning with Bayesian Optimization

Marco, A., Berkenkamp, F., Hennig, P., Schoellig, A. P., Krause, A., Schaal, S., Trimpe, S.

In Proceedings of the IEEE International Conference on Robotics and Automation (ICRA), pages: 1557-1563, IEEE, Piscataway, NJ, USA, IEEE International Conference on Robotics and Automation (ICRA), May 2017 (inproceedings)

am ics pn

PDF arXiv ICRA 2017 Spotlight presentation Virtual vs. Real - Video explanation DOI Project Page [BibTex]

PDF arXiv ICRA 2017 Spotlight presentation Virtual vs. Real - Video explanation DOI Project Page [BibTex]


no image
An automatic method for discovering rational heuristics for risky choice

Lieder, F., Krueger, P. M., Griffiths, T. L.

In Proceedings of the 39th Annual Meeting of the Cognitive Science Society. Austin, TX: Cognitive Science Society, 2017, Falk Lieder and Paul M. Krueger contributed equally to this publication. (inproceedings)

Abstract
What is the optimal way to make a decision given that your time is limited and your cognitive resources are bounded? To answer this question, we formalized the bounded optimal decision process as the solution to a meta-level Markov decision process whose actions are costly computations. We approximated the optimal solution and evaluated its predictions against human choice behavior in the Mouselab paradigm, which is widely used to study decision strategies. Our computational method rediscovered well-known heuristic strategies and the conditions under which they are used, as well as novel heuristics. A Mouselab experiment confirmed our model’s main predictions. These findings are a proof-of-concept that optimal cognitive strategies can be automatically derived as the rational use of finite time and bounded cognitive resources.

re

Project Page [BibTex]

Project Page [BibTex]


no image
A reward shaping method for promoting metacognitive learning

Lieder, F., Krueger, P. M., Callaway, F., Griffiths, T. L.

In Proceedings of the Third Multidisciplinary Conference on Reinforcement Learning and Decision-Making, 2017 (inproceedings)

re

Project Page [BibTex]

Project Page [BibTex]


no image
When does bounded-optimal metareasoning favor few cognitive systems?

Milli, S., Lieder, F., Griffiths, T. L.

In AAAI Conference on Artificial Intelligence, 31, 2017 (inproceedings)

re

[BibTex]

[BibTex]


no image
The Structure of Goal Systems Predicts Human Performance

Bourgin, D., Lieder, F., Reichman, D., Talmon, N., Griffiths, T.

In Proceedings of the 39th Annual Meeting of the Cognitive Science Society, 2017 (inproceedings)

re

[BibTex]

[BibTex]


no image
Learning to (mis) allocate control: maltransfer can lead to self-control failure

Bustamante, L., Lieder, F., Musslick, S., Shenhav, A., Cohen, J.

In The 3rd Multidisciplinary Conference on Reinforcement Learning and Decision Making. Ann Arbor, Michigan, 2017 (inproceedings)

re

[BibTex]

[BibTex]


no image
Mouselab-MDP: A new paradigm for tracing how people plan

Callaway, F., Lieder, F., Krueger, P. M., Griffiths, T. L.

In The 3rd multidisciplinary conference on reinforcement learning and decision making, 2017 (inproceedings)

re

[BibTex]

[BibTex]


no image
Enhancing metacognitive reinforcement learning using reward structures and feedback

Krueger, P. M., Lieder, F., Griffiths, T. L.

In Proceedings of the 39th Annual Meeting of the Cognitive Science Society, 2017 (inproceedings)

re

Project Page Project Page [BibTex]

Project Page Project Page [BibTex]


no image
Helping people choose subgoals with sparse pseudo rewards

Callaway, F., Lieder, F., Griffiths, T. L.

In Proceedings of the Third Multidisciplinary Conference on Reinforcement Learning and Decision Making, 2017 (inproceedings)

re

[BibTex]

[BibTex]