arXiv · 2302.01491
DiSProD: Differentiable Symbolic Propagation of Distributions for Planning
Abstract
The paper introduces DiSProD, an online planner developed for environments with probabilistic transitions in continuous state and action spaces. DiSProD builds a symbolic graph that captures the distribution of future trajectories, conditioned on a given policy, using independence assumptions and approximate propagation of distributions. The symbolic graph provides a differentiable representation of the policy's value, enabling efficient gradient-based optimization for long-horizon search. The propagation of approximate distributions can be seen as an aggregation of many trajectories, making it well-suited for dealing with sparse rewards and stochastic environments. An extensive experimental evaluation compares DiSProD to state-of-the-art planners in discrete-time planning and real-time control of robotic systems. The proposed method improves over existing planners in handling stochastic environments, sensitivity to search depth, sparsity of rewards, and large action spaces. Additional real-world experiments demonstrate that DiSProD can control ground vehicles and surface vessels to successfully navigate around obstacles.
Explore related subjects
Keep this discovery
Explore connections, maps & timelines
Palash Chatterjee, Ashutosh Chapagain, Weizhe Chen, Roni Khardon. 2023-02-03. DiSProD: Differentiable Symbolic Propagation of Distributions for Planning. https://arxiv.org/abs/2302.01491
Cite the original work for its findings. Save a collection to share your selection of sources.