Two-Step Reinforcement Learning for Multistage Strategy Card Game.
Konrad GodlewskiBartosz SawickiPublished in: CoRR (2023)
Keyphrases
- multistage
- reinforcement learning
- card game
- dynamic programming
- optimal policy
- production system
- single stage
- stochastic programming
- card games
- markov decision processes
- lot sizing
- state space
- post processing
- learning process
- imperfect information
- multi agent
- perfect information
- statistically significant
- optimal strategy
- long run