Memory-Based Explainable Reinforcement Learning.
Francisco CruzRichard DazeleyPeter VamplewPublished in: Australasian Conference on Artificial Intelligence (2019)
Keyphrases
- reinforcement learning
- function approximation
- state space
- machine learning
- model free
- reinforcement learning algorithms
- temporal difference
- information systems
- multi agent
- memory based learning
- optimal policy
- temporal difference learning
- function approximators
- control problems
- markov decision processes
- database
- learning algorithm
- databases
- policy search
- multi agent reinforcement learning
- continuous state
- evaluation function
- supervised learning
- evolutionary algorithm