Multi-agent cooperative area coverage: A two-stage planning approach based on reinforcement learning.
Guohui YuanJian XiaoJinhui HeHonyu JiaYaoting WangZhuoran WangPublished in: Inf. Sci. (2024)
Keyphrases
- reinforcement learning
- action selection
- function approximation
- model free
- planning problems
- partially observable
- learning algorithm
- multi agent
- macro actions
- reinforcement learning algorithms
- state space
- partial observability
- ai planning
- temporal difference
- decision support
- stochastic domains
- plan generation
- complex domains
- neural network
- supervised learning
- dynamic programming
- goal oriented
- deterministic domains
- function approximators
- learning classifier systems
- markov decision problems
- reinforcement learning problems
- mixed initiative
- markov decision processes
- heuristic search
- optimal policy
- mobile robot
- learning process
- search space
- machine learning