Combining Policy Search with Planning in Multi-agent Cooperation.
Jie MaStephen CameronPublished in: RoboCup (2008)
Keyphrases
- policy search
- multi agent cooperation
- reinforcement learning
- partially observable markov decision processes
- multi agent
- multi agent systems
- continuous state
- planning problems
- game theory
- heuristic search
- reinforcement learning algorithms
- markov decision problems
- continuous action
- machine learning
- markov chain
- reward function
- cooperative
- cooperative problem solving