Actor-Critic Policy Optimization in Partially Observable Multiagent Environments.
Sriram SrinivasanMarc LanctotVinícius Flores ZambaldiJulien PérolatKarl TuylsRémi MunosMichael BowlingPublished in: CoRR (2018)
Keyphrases
- partially observable
- actor critic
- reinforcement learning
- markov decision processes
- policy iteration
- infinite horizon
- partially observable markov decision processes
- state space
- policy gradient
- dynamical systems
- markov decision problems
- decision problems
- optimal control
- reinforcement learning algorithms
- approximate dynamic programming
- reward function
- average reward
- optimal policy
- temporal difference
- learning agent
- optimization problems
- neuro fuzzy
- function approximation
- learning algorithm
- dynamic programming
- multi agent
- markov decision process
- model free
- action space