Survivable Robotic Control through Guided Bayesian Policy Search with Deep Reinforcement Learning.
Sayyed Jaffar Ali RazaApan DastiderMingjie LinPublished in: CASE (2021)
Keyphrases
- robotic control
- policy search
- reinforcement learning
- continuous state
- reinforcement learning algorithms
- function approximation
- markov decision processes
- state space
- temporal difference
- dynamic programming
- optimal policy
- model free
- function approximators
- reward function
- multi agent
- reinforcement learning methods
- bayesian networks
- machine learning
- optimal control
- partially observable markov decision processes
- learning agent
- path planning
- policy gradient
- learning algorithm