Towards automating Codenames spymasters with deep reinforcement learning.
Sherman SiuPublished in: CoRR (2022)
Keyphrases
- perceptual aliasing
- reinforcement learning
- state space
- function approximation
- dynamic programming
- temporal difference
- model free
- markov decision processes
- policy search
- reinforcement learning algorithms
- database
- search engine
- learning algorithm
- machine learning
- evaluation function
- least squares
- learning process
- learning agents
- multi agent reinforcement learning