Reinforcement learning for multi-agent patrol policy.
Zhaohui HuDongbin ZhaoPublished in: IEEE ICCI (2010)
Keyphrases
- reinforcement learning
- multi agent
- optimal policy
- policy search
- markov decision process
- action selection
- control policy
- control policies
- function approximation
- state space
- partially observable
- markov decision problems
- policy iteration
- reinforcement learning algorithms
- function approximators
- reinforcement learning problems
- actor critic
- rl algorithms
- markov decision processes
- action space
- policy evaluation
- approximate dynamic programming
- policy gradient
- reward function
- cooperative
- single agent
- partially observable markov decision processes
- state action
- partially observable environments
- learning agents
- transfer learning
- temporal difference
- intelligent agents
- continuous state
- markov games
- agent learns
- average reward
- multiagent systems
- finite state
- continuous state spaces
- model free
- multi agent environments
- heterogeneous agents
- machine learning
- partially observable domains
- infinite horizon
- multi robot
- decision problems
- learning process
- multi agent systems
- multi agent reinforcement learning
- optimal control
- autonomous agents
- learning algorithm
- search and rescue
- reinforcement learning methods
- control problems
- transition model
- inverse reinforcement learning
- dynamic programming