Towards Reinforcement Learning for Non-stationary Environments.
Sebastian Gregory Dal ToéBernard TiddemanNeil Mac ParthaláinPublished in: UKCI (2023)
Keyphrases
- reinforcement learning
- function approximation
- multi agent
- reinforcement learning algorithms
- model free
- robotic control
- markov decision processes
- state space
- machine learning
- multi agent reinforcement learning
- learning algorithm
- control problems
- temporal difference
- learning problems
- optimal policy
- action selection
- practical problems
- function approximators
- learning agents
- temporal difference learning
- autonomous learning
- bayesian networks
- relational reinforcement learning
- e learning