Keyphrases
- gradient method
- markov games
- markov decision process
- markov decision processes
- multiagent reinforcement learning
- reinforcement learning algorithms
- policy gradient
- reinforcement learning
- optimal policy
- convergence rate
- control problems
- state space
- step size
- negative matrix factorization
- optimization methods
- nash equilibrium
- infinite horizon
- finite horizon
- stochastic games
- multiagent systems
- reward function
- policy iteration
- initial state
- dynamic programming
- average reward
- cooperative
- temporal difference
- model free
- finite state
- multi agent
- data mining
- partially observable
- average cost
- pairwise
- long run
- function approximation
- objective function