Graphical Minimax Game and On-Policy Reinforcement Learning for Consensus of Leaderless Multi-Agent Systems.
Wei DongChunyan WangJinna LiJianan WangPublished in: ICCA (2020)
Keyphrases
- reinforcement learning
- multi agent systems
- game theory
- optimal policy
- agent learns
- policy search
- multi agent
- multi agent reinforcement learning
- markov decision process
- imperfect information
- markov games
- game tree
- game theoretic
- action selection
- reinforcement learning algorithms
- reinforcement learning problems
- stochastic games
- partially observable environments
- state space
- nash equilibrium
- function approximators
- rl algorithms
- action space
- game playing
- decision problems
- minimax search
- actor critic
- control policy
- single agent
- markov decision processes
- cooperative
- computer games
- policy iteration
- function approximation
- markov decision problems
- partially observable
- state and action spaces
- model free
- temporal difference learning
- multi agent environments
- agent systems
- policy evaluation
- policy gradient
- video games
- multi agent learning
- reward function
- optimal strategy
- reinforcement learning methods
- dynamic programming
- state action
- agent architecture
- partially observable markov decision processes
- autonomous agents
- intelligent agents
- temporal difference
- learning algorithm
- coalition formation
- nash equilibria
- game play
- alpha beta
- perfect information
- agent technology
- control policies
- multiagent systems
- mobile robot
- inverse reinforcement learning
- resource allocation
- infinite horizon
- partially observable domains
- long run
- software agents
- monte carlo
- continuous state
- educational games
- serious games