Mastering 2048 with Delayed Temporal Coherence Learning, Multi-Stage Weight Promotion, Redundant Encoding and Carousel Shaping
[ 1 ] Instytut Informatyki, Wydział Informatyki, Politechnika Poznańska | [ 2 ] Swiss AI Lab IDSIA (Dalle Molle Institute for Artificial Intelligence Research) | [ P ] pracownik
2018
artykuł naukowy
angielski
- n-tuple system
- reinforcement learning
- temporal coherence
- 2048 game
- tile coding
- function approximation
- Markov decision process
- MDP
11.01.2017
1 - 13
15
15