Entropy Regularized Motion Planning via Stein Variational Inference
This addresses the challenge of obtaining reliable trajectory distributions for imitation and reinforcement learning in robotics, though it appears incremental as it builds on existing variational inference and motion planning methods.
The paper tackles the problem of generating diverse, feasible trajectories for high-dof motion planning by proposing a sampling strategy based on variational inference, resulting in a distributed, particle-based algorithm that connects to trajectory optimization and entropy-regularized RL.
Many Imitation and Reinforcement Learning approaches rely on the availability of expert-generated demonstrations for learning policies or value functions from data. Obtaining a reliable distribution of trajectories from motion planners is non-trivial, since it must broadly cover the space of states likely to be encountered during execution while also satisfying task-based constraints. We propose a sampling strategy based on variational inference to generate distributions of feasible, low-cost trajectories for high-dof motion planning tasks. This includes a distributed, particle-based motion planning algorithm which leverages a structured graphical representations for inference over multi-modal posterior distributions. We also make explicit connections to both approximate inference for trajectory optimization and entropy-regularized reinforcement learning.