Stable Reinforcement Learning with Unbounded State Space.
Devavrat ShahQiaomin XieZhi XuPublished in: L4DC (2020)
Keyphrases
- state space
- reinforcement learning
- reinforcement learning algorithms
- markov decision processes
- optimal policy
- heuristic search
- markov decision process
- markov chain
- function approximation
- action space
- partially observable
- dynamic programming
- continuous state spaces
- dynamical systems
- control problems
- state variables
- machine learning
- planning problems
- particle filter
- goal state
- temporal difference
- reward function
- reinforcement learning methods
- search space
- multi agent
- state abstraction
- learning algorithm
- supervised learning
- complex domains
- initial state
- finite state
- optimal control
- temporal difference learning
- learning problems
- markov decision problems
- transfer learning
- learning process
- policy search
- state and action spaces
- reward shaping
- robotic control