Tackling Unbounded State Spaces in Continuing Task Reinforcement Learning.
Brahma S. PavseYudong ChenQiaomin XieJosiah P. HannaPublished in: CoRR (2023)
Keyphrases
- state space
- reinforcement learning
- reinforcement learning algorithms
- markov decision processes
- optimal policy
- heuristic search
- orders of magnitude
- function approximation
- model free
- dynamic programming
- state abstraction
- temporal difference
- markov chain
- action space
- markov decision process
- particle filter
- planning problems
- partially observable
- robotic control
- control problems
- continuous state spaces
- dynamical systems
- transfer learning
- belief state
- action selection
- supervised learning
- pattern databases
- learning algorithm
- reward function
- optimal control
- reinforcement learning methods
- partial observability
- learning process
- multi agent