2007
NeurIPS
NeurIPS 2007
Random Sampling of States in Dynamic Programming
Abstract
We combine two threads of research on approximate dynamic programming: random sampling of states and using local trajectory optimizers to globally optimize a policy and associated value function. This combination allows us to replace a dense multidimensional grid with a much sparser adaptive sampling of states. Our focus is on finding steady state policies for the deterministic time invariant discrete time control problems with continuous states and actions often found in robotics. In this paper we show that we can now solve problems we couldn't solve previously with regular grid-based approaches.
🌉
Interdisciplinary Bridge
- Artificial Intelligence and Computer Science and Reinforcement Learning and Robotics
📈
Trend Setter
- Robotics
🧭
Keyword Pioneer
- trajectory optimization
🐣
Hot Topic Early Bird
- value function
Authors
Topics
Artificial Intelligence > Core AI > Planning
Machine Learning > Optimization & Theory > Optimization
Reinforcement Learning > Methods > Deep RL
Reinforcement Learning > Methods > Policy Learning
Reinforcement Learning > Applications > Robotics
Reinforcement Learning > Applications > Value Iteration
Robotics > Capabilities > Motion Planning
Computer Science > Foundations > Algorithms
Robotics > Applications > Robotics