Entropy Regularized Motion Planning via Stein Variational Inference
arXiv:2107.05146
Abstract
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.
arXiv commentRSS 2021 Workshop on Integrating Planning and Learning
References in corpus (8)
- Reinforcement Learning with Deep Energy-Based Policies
- Reinforcement Learning and Control as Probabilistic Inference: Tutorial and Review
- Continuous-Time Gaussian Process Motion Planning via Probabilistic Inference
- Non-Smooth Newton Methods for Deformable Multi-Body Dynamics
- Stein Variational Gradient Descent With Matrix-Valued Kernels
- Stein Point Markov Chain Monte Carlo
- Approximate Inference and Stochastic Optimal Control
- Local Search for Policy Iteration in Continuous Control