Hierarchical Width-Based Planning and Learning
Junyent, Miquel, Gómez, Vicenç, Jonsson, Anders
–arXiv.org Artificial Intelligence
Width-based search methods have demonstrated state-of-the-art performance in a wide range of testbeds, from classical planning problems to image-based simulators such as Atari games. These methods scale independently of the size of the state-space, but exponentially in the problem width. In practice, running the algorithm with a width larger than 1 is computationally intractable, prohibiting IW from solving higher width problems. In this paper, we present a hierarchical algorithm that plans at two levels of abstraction. A high-level planner uses abstract features that are incrementally discovered from low-level pruning decisions. We illustrate this algorithm in classical planning PDDL domains as well as in pixel-based simulator domains. In classical planning, we show how IW(1) at two levels of abstraction can solve problems of width 2. For pixel-based domains, we show how in combination with a learned policy and a learned value function, the proposed hierarchical IW can outperform current flat IW-based planners in Atari games with sparse rewards.
arXiv.org Artificial Intelligence
Jan-15-2021
- Country:
- Europe (0.28)
- North America > United States (0.28)
- Genre:
- Research Report (0.50)
- Industry:
- Leisure & Entertainment > Games > Computer Games (1.00)
- Technology: