Explainability in deep reinforcement learning.
Alexandre HeuilletFabien CouthouisNatalia Díaz RodríguezPublished in: Knowl. Based Syst. (2021)
Keyphrases
- reinforcement learning
- function approximation
- state space
- dynamic programming
- machine learning
- temporal difference learning
- control problems
- temporal difference
- markov decision processes
- information retrieval
- policy search
- robot control
- model free
- optimal policy
- multi agent
- multiscale
- information systems
- learning algorithm
- hidden markov models
- reinforcement learning algorithms
- partially observable
- continuous state
- multi agent reinforcement learning
- genetic algorithm
- active exploration
- robotic control