Reinforcement Learning in Non-Markovian Environments.
Siddharth ChandakVivek S. BorkarParth DodhiaPublished in: CoRR (2022)
Keyphrases
- stochastic process
- reinforcement learning
- stochastic model
- function approximation
- state space
- dynamic environments
- markov decision processes
- learning algorithm
- machine learning
- optimal policy
- multi agent environments
- stochastic approximation
- dynamic programming
- learning process
- multi agent
- learning problems
- decision problems
- complex environments
- model free
- highly dynamic
- reinforcement learning algorithms
- markov decision process
- search algorithm
- policy search