Multi-Agent Synchronization Using Online Model-Free Action Dependent Dual Heuristic Dynamic Programming Approach.
Mohammed I. AbouheafWail GueaiebPublished in: ICRA (2019)
Keyphrases
- model free
- dynamic programming
- reinforcement learning
- multi agent
- reinforcement learning algorithms
- function approximation
- temporal difference
- state space
- action selection
- dynamic programming algorithms
- optimal control
- optimal policy
- policy iteration
- action space
- linear programming
- supervised learning
- optimal solution
- markov decision processes
- lagrangian relaxation
- partially observable markov decision processes
- infinite horizon
- learning process
- data mining
- partially observable
- neural network