Improving Deep Reinforcement Learning in Minecraft with Action Advice.
Spencer FrazierMark RiedlPublished in: AIIDE (2019)
Keyphrases
- reinforcement learning
- action selection
- partially observable domains
- action space
- state action
- reinforcement learning algorithms
- function approximation
- transition model
- model free
- machine learning
- deep learning
- computer vision
- data sets
- markov decision processes
- least squares
- state space
- learning process
- multi agent
- multi agent reinforcement learning
- reward shaping
- fitted q iteration