Deep Reinforcement Learning for Time Optimal Velocity Control using Prior Knowledge.
Gabriel HartmannZvi ShillerAmos AzariaPublished in: ICTAI (2019)
Keyphrases
- optimal control
- reinforcement learning
- prior knowledge
- control policy
- control problems
- dynamic programming
- control system
- control strategy
- optimal solution
- control policies
- robot control
- prior information
- worst case
- multi agent
- model free
- average cost
- state space
- kinematic model
- image sequences
- mechanical systems
- stochastic control
- motion control
- function approximation
- domain knowledge