Leveraging Statistical Multi-Agent Online Planning with Emergent Value Function Approximation.
Thomy PhanLenz BelznerThomas GaborKyrill SchmidPublished in: AAMAS (2018)
Keyphrases
- multi agent
- online learning
- cooperative
- intelligent agents
- multi agent planning
- statistical models
- data driven
- reinforcement learning
- state space
- statistical analysis
- basis functions
- domain independent
- multi agent systems
- heuristic search
- statistical information
- search space
- real time
- planning domains
- temporal difference
- path finding
- stochastic domains
- neural network