Policy Adaptive Multi-agent Deep Deterministic Policy Gradient.
Yixiang WangFeng WuPublished in: PRIMA (2020)
Keyphrases
- policy gradient
- multi agent
- actor critic
- reinforcement learning
- single agent
- model free reinforcement learning
- policy search
- partially observable markov decision processes
- policy gradient methods
- gradient method
- function approximation
- optimal control
- multi agent systems
- reinforcement learning algorithms
- cooperative
- neural network
- approximation methods
- optimal policy
- machine learning
- multiple agents
- state space
- approximate dynamic programming
- reinforcement learning methods
- average reward
- variance reduction
- state action
- domain independent
- function approximators
- markov decision processes
- learning algorithm
- negative matrix factorization