Reinforcement Learning with Reward Machines in Stochastic Games.
Jueming HuJean-Raphaël GaglioneYanze WangZhe XuUfuk TopcuYongming LiuPublished in: ECAI (2023)
Keyphrases
- stochastic games
- reinforcement learning
- average reward
- reinforcement learning algorithms
- markov decision processes
- learning agent
- optimal policy
- state action
- learning automata
- multi agent reinforcement learning
- model free
- multiagent reinforcement learning
- reward function
- state space
- function approximation
- multi agent
- single agent
- rl algorithms
- nash equilibria
- learning algorithm
- temporal difference
- policy iteration
- action selection
- long run
- finite state
- dynamic programming
- learning process
- repeated games
- computational complexity
- function approximators
- nash equilibrium
- supervised learning
- machine learning