A Two-stage Reinforcement Learning-based Approach for Multi-entity Task Allocation.
Aicheng GongKai YangJiafei LyuXiu LiPublished in: CoRR (2024)
Keyphrases
- reinforcement learning
- entity identification
- function approximation
- multi agent systems
- state space
- optimal policy
- temporal difference learning
- markov decision processes
- optimal control
- coalition formation
- model free
- robotic control
- data sets
- autonomous learning
- robot control
- partially observable
- reinforcement learning algorithms
- learning classifier systems
- named entities
- learning process
- information retrieval
- neural network