Timezone: »

 
Learning Space Partitions for Path Planning
Kevin Yang · Tianjun Zhang · Chris Cummins · Brandon Cui · Benoit Steiner · Linnan Wang · Joseph E Gonzalez · Dan Klein · Yuandong Tian

@
in Reinforcement Learning for Real Life »

Path planning, the problem of efficiently discovering high-reward trajectories, often requires optimizing a high-dimensional and multimodal reward function. Popular approaches like CEM and CMA-ES greedily focus on promising regions of the search space and may get trapped in local maxima. DOO and VOOT balance exploration and exploitation, but use space partitioning strategies independent of the reward function to be optimized. Recently, LaMCTS empirically learns to partition the search space in a reward-sensitive manner for black-box optimization. In this paper, we develop a novel formal regret analysis for when and why such an adaptive region partitioning scheme works. We also propose a new path planning method PlaLaM which improves the function value estimation within each sub-region, and uses a latent representation of the search space. Empirically, PlaLaM outperforms existing path planning methods in 2D navigation tasks, especially in the presence of difficult-to-escape local optima, and shows benefits when plugged into model-based RL with planning components such as PETS. These gains transfer to highly multimodal real-world tasks, where we outperform strong baselines in compiler phase ordering by up to 245% and in molecular design by up to 0.4 on properties on a 0-1 scale. Code is available at https://github.com/yangkevin2/plalam.

Author Information

Kevin Yang (UC Berkeley)
Tianjun Zhang (UC Berkeley)
Chris Cummins (Facebook AI Research)
Brandon Cui (Facebook AI Research)
Benoit Steiner (FAIR)
Linnan Wang (Brown)
Joseph E Gonzalez (UC Berkeley)
Dan Klein (UC Berkeley)
Yuandong Tian (Facebook AI Research)

More from the Same Authors