Improving Deep Reinforcement Learning in Minecraft with Action Advice.
Spencer FrazierMark RiedlPublished in: CoRR (2019)
Keyphrases
- reinforcement learning
- action selection
- action space
- reward shaping
- function approximation
- learning algorithm
- state action
- partially observable domains
- state space
- multi agent
- machine learning
- reinforcement learning algorithms
- markov decision processes
- human actions
- learning process
- temporal difference
- website
- transition model
- state and action spaces
- neural network