DRLViz: Understanding Decisions and Memory in Deep Reinforcement Learning.
Theo JaunetRomain VuillemotChristian WolfPublished in: Comput. Graph. Forum (2020)
Keyphrases
- reinforcement learning
- decision makers
- decision making
- memory usage
- markov decision processes
- data mining
- multi agent
- state space
- model free
- machine learning
- limited memory
- computing power
- reinforcement learning algorithms
- temporal difference
- function approximation
- supervised learning
- main memory
- dynamic programming
- case study
- artificial intelligence
- genetic algorithm
- temporal difference learning
- strategic decisions