A Pontryagin Perspective on Reinforcement Learning.
Onno EberhardClaire VernadeMichael MuehlebachPublished in: CoRR (2024)
Keyphrases
- reinforcement learning
- markov decision processes
- multi agent
- viewpoint
- state space
- robotic control
- learning algorithm
- function approximation
- neural network
- reinforcement learning algorithms
- action selection
- dynamic environments
- information systems
- dynamic programming
- case study
- optimal policy
- website
- artificial intelligence
- information retrieval
- learning capabilities
- partially observable
- learning agents
- multi agent reinforcement learning
- transition model
- databases
- direct policy search