Quantitative Planning with Action Deception in Concurrent Stochastic Games.
Chongyang ShiShuo HanJie FuPublished in: AAMAS (2023)
Keyphrases
- stochastic games
- state action
- nash equilibria
- single agent
- action selection
- markov decision processes
- multiagent reinforcement learning
- incomplete information
- multi agent
- learning automata
- initial state
- imperfect information
- average reward
- repeated games
- machine learning
- domain independent
- cooperative
- robust optimization
- dynamic environments
- path finding
- mixed initiative
- optimal policy
- learning agent
- infinite horizon
- decision theoretic
- function approximation
- reinforcement learning
- multiagent systems
- game theory