Schultheis, Matthias ; Belousov, Boris ; Abdulsamad, Hany ; Peters, Jan (2022)
Receding Horizon Curiosity.
3rd Conference on Robot Learning (CoRL 2019). Osaka, Japan (30.10.- 1.11.2019)
doi: 10.26083/tuprints-00020578
Konferenzveröffentlichung, Zweitveröffentlichung, Verlagsversion
 | Es ist eine neuere Version dieses Eintrags verfügbar. |
Kurzbeschreibung (Abstract)
Sample-efficient exploration is crucial not only for discovering rewarding experiences but also for adapting to environment changes in a task-agnostic fashion. A principled treatment of the problem of optimal input synthesis for system identification is provided within the framework of sequential Bayesian experimental design. In this paper, we present an effective trajectory-optimization-based approximate solution of this otherwise intractable problem that models optimal exploration in an unknown Markov decision process (MDP). By interleaving episodic exploration with Bayesian nonlinear system identification, our algorithm takes advantage of the inductive bias to explore in a directed manner, without assuming prior knowledge of the MDP. Empirical evaluations indicate a clear advantage of the proposed algorithm in terms of the rate of convergence and the final model fidelity when compared to intrinsic-motivation-based algorithms employing exploration bonuses such as prediction error and information gain. Moreover, our method maintains a computational advantage over a recent model-based active exploration (MAX) algorithm, by focusing on the information gain along trajectories instead of seeking a global exploration policy. A reference implementation of our algorithm and the conducted experiments is publicly available.
| Typ des Eintrags: | Konferenzveröffentlichung |
|---|---|
| Erschienen: | 2022 |
| Autor(en): | Schultheis, Matthias ; Belousov, Boris ; Abdulsamad, Hany ; Peters, Jan |
| Art des Eintrags: | Zweitveröffentlichung |
| Titel: | Receding Horizon Curiosity |
| Sprache: | Englisch |
| Publikationsjahr: | 2022 |
| Ort: | Darmstadt |
| Publikationsdatum der Erstveröffentlichung: | 2022 |
| Verlag: | PMLR |
| Reihe: | Proceedings of Machine Learning Research |
| Band einer Reihe: | 100 |
| Kollation: | 11 Seiten |
| Veranstaltungstitel: | 3rd Conference on Robot Learning (CoRL 2019) |
| Veranstaltungsort: | Osaka, Japan |
| Veranstaltungsdatum: | 30.10.- 1.11.2019 |
| DOI: | 10.26083/tuprints-00020578 |
| URL / URN: | https://tuprints.ulb.tu-darmstadt.de/20578 |
| Zugehörige Links: | |
| Herkunft: | Zweitveröffentlichungsservice |
| Kurzbeschreibung (Abstract): | Sample-efficient exploration is crucial not only for discovering rewarding experiences but also for adapting to environment changes in a task-agnostic fashion. A principled treatment of the problem of optimal input synthesis for system identification is provided within the framework of sequential Bayesian experimental design. In this paper, we present an effective trajectory-optimization-based approximate solution of this otherwise intractable problem that models optimal exploration in an unknown Markov decision process (MDP). By interleaving episodic exploration with Bayesian nonlinear system identification, our algorithm takes advantage of the inductive bias to explore in a directed manner, without assuming prior knowledge of the MDP. Empirical evaluations indicate a clear advantage of the proposed algorithm in terms of the rate of convergence and the final model fidelity when compared to intrinsic-motivation-based algorithms employing exploration bonuses such as prediction error and information gain. Moreover, our method maintains a computational advantage over a recent model-based active exploration (MAX) algorithm, by focusing on the information gain along trajectories instead of seeking a global exploration policy. A reference implementation of our algorithm and the conducted experiments is publicly available. |
| Freie Schlagworte: | Bayesian exploration, artificial curiosity, model predictive control |
| Status: | Verlagsversion |
| URN: | urn:nbn:de:tuda-tuprints-205782 |
| Sachgruppe der Dewey Dezimalklassifikatin (DDC): | 000 Allgemeines, Informatik, Informationswissenschaft > 004 Informatik |
| Fachbereich(e)/-gebiet(e): | 20 Fachbereich Informatik 20 Fachbereich Informatik > Intelligente Autonome Systeme |
| TU-Projekte: | EC/H2020|640554|SKILLS4ROBOTS |
| Hinterlegungsdatum: | 18 Nov 2022 14:27 |
| Letzte Änderung: | 25 Apr 2023 12:06 |
| PPN: | 502453915 |
| Export: | |
| Suche nach Titel in: | TUfind oder in Google |
Verfügbare Versionen dieses Eintrags
- Receding Horizon Curiosity. (deposited 18 Nov 2022 14:27) [Gegenwärtig angezeigt]
 |
Frage zum Eintrag |
Optionen (nur für Redakteure)
 |
Redaktionelle Details anzeigen |
Drucken
Impressum