A Multi-Agent Prediction Market based on Partially Observable Stochastic Game
Janyl JumadinovaPrithviraj DasguptaPublished in: CoRR (2012)
Keyphrases
- partially observable
- multi agent
- reinforcement learning
- decision problems
- game theoretic
- state space
- dynamical systems
- partial observability
- markov decision processes
- fully observable
- partial observations
- infinite horizon
- partially observable environments
- action models
- game theory
- initially unknown
- belief state
- markov decision problems
- reward function
- multiple agents
- multi agent systems
- partially observable markov decision processes
- nash equilibrium
- belief space
- monte carlo
- rational agents
- partially observable domains
- optimal policy
- optimal strategy
- multiagent systems
- single agent
- reinforcement learning algorithms
- coalition formation
- optimal control
- domain independent
- heuristic search
- domain specific
- learning algorithm