# Receding Horizon Curiosity

arXiv: https://arxiv.org/abs/1910.03620 · HTML: https://mlsanity.com/paper/1910.03620/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Oct 2019.

## Built on by (most cited first, 10 of 10)

- [Interesting Object, Curious Agent: Learning Task-Agnostic Exploration](https://mlsanity.com/paper/2111.13119/) (2021)
- [A Probabilistic Interpretation of Self-Paced Learning with Applications to Reinforcement Learning](https://mlsanity.com/paper/2102.13176/) (2021)
- [Nesting Particle Filters for Experimental Design in Dynamical Systems](https://mlsanity.com/paper/2402.07868/) (2024)
- [Exploration via Planning for Information about the Optimal Trajectory](https://mlsanity.com/paper/2210.04642/) (2022)
- [Bridging Active Exploration and Uncertainty-Aware Deployment Using Probabilistic Ensemble Neural Network Dynamics](https://mlsanity.com/paper/2305.12240/) (2023)
- [FLEX: an Adaptive Exploration Algorithm for Nonlinear Systems](https://mlsanity.com/paper/2304.13426/) (2023)
- [Human-Inspired Framework to Accelerate Reinforcement Learning](https://mlsanity.com/paper/2303.08115/) (2023)
- [Maximin Robust Bayesian Experimental Design](https://mlsanity.com/paper/2603.14094/) (2026)
- [Trajectory Design and Budgeted Querying for Digital Twin Calibration](https://mlsanity.com/paper/2608.08631/) (2026)
- [Information-theoretic receding-horizon active learning of nonlinear dynamical systems](https://mlsanity.com/paper/2609.36712/) (2026)

## Abstract (arXiv)

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.