Reinforcement Learning With Reward Machines in Stochastic Games.
Jueming HuJean-Raphaël GaglioneYanze WangZhe XuUfuk TopcuYongming LiuPublished in: CoRR (2023)
Keyphrases
- stochastic games
- reinforcement learning
- average reward
- reinforcement learning algorithms
- markov decision processes
- learning agent
- state action
- optimal policy
- learning automata
- multi agent reinforcement learning
- reward function
- model free
- multiagent reinforcement learning
- multi agent
- state space
- single agent
- rl algorithms
- function approximation
- long run
- nash equilibria
- policy iteration
- partially observable
- supervised learning
- repeated games
- machine learning
- dynamic programming
- learning capabilities
- transfer learning
- learning algorithm
- markov decision process
- finite state
- decision problems
- nash equilibrium
- infinite horizon