Automated Pricing in a Multiagent Prediction Market Using a Partially Observable Stochastic Game.
Janyl JumadinovaPrithviraj DasguptaPublished in: ACM Trans. Intell. Syst. Technol. (2015)
Keyphrases
- partially observable
- multi agent
- decision problems
- dynamical systems
- reinforcement learning
- markov decision processes
- state space
- partial observability
- infinite horizon
- dec pomdps
- fully observable
- markov decision problems
- partial observations
- planning under uncertainty
- partially observable markov decision process
- multiagent systems
- initially unknown
- optimal strategy
- partially observable environments
- reward function
- action models
- nash equilibrium
- game theory
- partially observable domains
- multiple agents
- belief state
- planning domains
- partially observable markov decision processes
- single agent
- optimal policy
- multi agent systems
- machine learning
- monte carlo
- sufficient conditions
- np hard
- optimal solution
- learning algorithm