The limits and robustness of reinforcement learning in Lewis signalling games.
David CatteeuwBernard ManderickPublished in: Connect. Sci. (2014)
Keyphrases
- reinforcement learning
- learning agents
- action sets
- state space
- markov decision processes
- video games
- computer games
- nash equilibria
- learning algorithm
- robotic control
- temporal difference learning
- function approximation
- game theoretic
- computational efficiency
- multi agent
- machine learning
- nash equilibrium
- game play
- game playing
- model free
- reinforcement learning algorithms
- learning agent
- dynamic programming
- transition model
- weighted majority