Attention Actor-Critic algorithm for Multi-Agent Constrained Co-operative Reinforcement Learning.
P. ParnikaRaghuram Bharadwaj DiddigiSai Koti Reddy DandaShalabh BhatnagarPublished in: CoRR (2021)
Keyphrases
- reinforcement learning
- multi agent
- actor critic
- cooperative
- learning algorithm
- objective function
- computational complexity
- dynamic programming
- optimal solution
- np hard
- particle swarm optimization
- model free
- monte carlo
- optimal control
- rl algorithms
- policy gradient
- natural actor critic
- simulated annealing
- neural network
- markov decision processes
- optimization method
- convergence rate
- least squares
- reinforcement learning algorithms
- policy iteration
- cost function