A comment on stabilizing reinforcement learning.
Pavel OsinenkoGeorgiy MalaniyaGrigory YaremenkoIlya OsokinPublished in: CoRR (2021)
Keyphrases
- reinforcement learning
- function approximation
- state space
- model free
- markov decision processes
- robotic control
- reinforcement learning algorithms
- learning process
- temporal difference
- machine learning
- control problems
- relational reinforcement learning
- optimal policy
- multi agent
- temporal difference learning
- optimal control
- nonlinear systems
- artificial intelligence
- database
- continuous state
- control policy
- markov decision process
- evolutionary algorithm
- learning classifier systems
- search engine
- supervised learning
- dynamic programming
- hidden markov models