Pheromone-Based Planning Strategies in Dyna-Q Learning.
Kao-Shing HwangWei-Cheng JiangYu-Jen ChenPublished in: IEEE Trans. Ind. Informatics (2017)
Keyphrases
- function approximation
- temporal difference learning
- reinforcement learning
- action selection
- planning problems
- state space
- heuristic search
- cooperative
- multi agent
- ant colony optimization
- learning algorithm
- ai planning
- planning process
- optimal policy
- domain independent
- search space
- online auctions
- partially observable
- function approximators
- multi agent reinforcement learning