Reinforcement learning in non-Markovian environments.
Siddharth ChandakPratik ShahVivek S. BorkarParth DodhiaPublished in: Syst. Control. Lett. (2024)
Keyphrases
- reinforcement learning
- function approximation
- reinforcement learning agents
- state space
- dynamic environments
- model free
- multi agent environments
- temporal difference
- partially observable domains
- reinforcement learning algorithms
- real world
- dynamic programming
- action selection
- stochastic process
- temporal difference learning
- markov decision processes
- transfer learning
- multi agent
- machine learning
- multi agent reinforcement learning
- database
- policy search
- state abstraction
- reinforcement learning methods
- knowledge base
- highly dynamic
- reward function
- multiple agents
- optimal policy