| 1. |
- Baumann, Dominik, Ph.D. 1991-, et al.
(författare)
-
A computationally lightweight safe learning algorithm
- 2023
-
Ingår i: 2023 62nd IEEE Conference on Decision and Control, (CDC). - : Institute of Electrical and Electronics Engineers (IEEE). - 9798350301243 - 9798350301250 ; , s. 1022-1027
-
Konferensbidrag (refereegranskat)abstract
- Safety is an essential asset when learning control policies for physical systems, as violating safety constraints during training can lead to expensive hardware damage. In response to this need, the field of safe learning has emerged with algorithms that can provide probabilistic safety guarantees without knowledge of the underlying system dynamics. Those algorithms often rely on Gaussian process inference. Unfortunately, Gaussian process inference scales cubically with the number of data points, limiting applicability to high-dimensional and embedded systems. In this paper, we propose a safe learning algorithm that provides probabilistic safety guarantees but leverages the Nadaraya-Watson estimator instead of Gaussian processes. For the Nadaraya-Watson estimator, we can reach logarithmic scaling with the number of data points. We provide theoretical guarantees for the estimates, embed them into a safe learning algorithm, and show numerical experiments on a simulated seven-degrees-of-freedom robot manipulator.
|
|
| 2. |
- Hulme, Oliver, et al.
(författare)
-
Reply to "The Limitations of Growth-Optimal Approaches to Decision Making Under Uncertainty"
- 2023
-
Ingår i: Econ Journal Watch. - : Institute of Spontaneous Order Economics. - 1933-527X. ; 20:2, s. 335-348
-
Tidskriftsartikel (övrigt vetenskapligt/konstnärligt)abstract
- In an article appearing concurrently with the present one, Matthew Ford and John Kay put forward their understanding of a decision theory which emerges in ergodicity economics. Their understanding leads them to believe that ergodicity economics evades the core problem of decisions under uncertainty and operates solely in a regime where there is no measurable uncertainty. If this were the case, then the authors' critical stance would be justified and, as the authors point out, the decision theory would yield only trivial results, identical to a flavor of expected-utility theory. Here we clarify that the critique is based on a theoretical misunderstanding, and that uncertainty-quantified in any reasonable way-is large in the regime where the model operates. Our resolution explains the success of recent laboratory experiments, where ergodicity economics makes predictions different from expected-utility theory, contrary to the claim of equivalence by Ford and Kay. Also, a state of the world is identified where ergodicity economics outperforms expected-utility theory empirically.
|
|
| 3. |
- Sukhija, Bhavya, et al.
(författare)
-
GOSAFEOPT : Scalable safe exploration for global optimization of dynamical systems
- 2023
-
Ingår i: Artificial Intelligence. - : Elsevier BV. - 0004-3702 .- 1872-7921. ; 320
-
Tidskriftsartikel (refereegranskat)abstract
- Learning optimal control policies directly on physical systems is challenging. Even a single failure can lead to costly hardware damage. Most existing model-free learning methods that guarantee safety, i.e., no failures, during exploration are limited to local optima. This work proposes GOSAFEOPT as the first provably safe and optimal algorithm that can safely discover globally optimal policies for systems with high-dimensional state space. We demonstrate the superiority of GOSAFEOPT over competing model-free safe learning methods in simulation and hardware experiments on a robot arm.(c) 2023 The Author(s). Published by Elsevier B.V. This is an open access article under the CC BY license (http://creativecommons .org /licenses /by /4 .0/).
|
|
