Loading...
Please wait, while we are loading the content...
Similar Documents
0 v 1 [ cs . L G ] 8 O ct 2 01 9 Receding Horizon Curiosity
| Content Provider | Semantic Scholar |
|---|---|
| Author | Schultheis, Matthias Belousov, Boris Abdulsamad, Hany Peters, Jan |
| Copyright Year | 2019 |
| 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-optimizationbased 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. |
| File Format | PDF HTM / HTML |
| Alternate Webpage(s) | https://export.arxiv.org/pdf/1910.03620 |
| Language | English |
| Access Restriction | Open |
| Content Type | Text |
| Resource Type | Article |
