Tutorial Educating Developer of Reinforcement Learning Agent Using IDEAL.
Takahiro UchiyaKodai ShimanoIchi TakumiPublished in: BWCCA (2019)
Keyphrases
- learning agent
- reinforcement learning
- state space
- learning algorithm
- reinforcement learning algorithms
- solving problems
- learning capabilities
- function approximation
- model free
- learning tasks
- learning process
- markov decision processes
- dynamic environments
- dynamic programming
- domain knowledge
- action selection
- temporal difference
- reward function
- multi agent
- single agent
- machine learning
- neural network
- supervised learning
- decision trees