Inverse reinforcement learning for video games.
Aaron TuckerAdam GleaveStuart RussellPublished in: CoRR (2018)
Keyphrases
- video games
- inverse reinforcement learning
- bayesian nonparametric
- partially observable environments
- preference elicitation
- learning experience
- reward function
- game play
- educational games
- game design
- game playing
- computer games
- learning environment
- temporal difference
- e learning
- serious games
- multi objective
- commercial games