DiffPoGAN: Diffusion Policies with Generative Adversarial Networks for Offline Reinforcement Learning.
Xuemin HuShen LiYingfen XuBo TangLong ChenPublished in: CoRR (2024)
Keyphrases
- reinforcement learning
- optimal policy
- policy search
- multi agent
- information diffusion
- real time
- social networks
- control policy
- markov decision processes
- anisotropic diffusion
- network analysis
- policy gradient methods
- markov decision process
- complex networks
- markov decision problems
- diffusion process
- network structure
- state space
- neural network
- decision problems
- partially observable markov decision processes
- monte carlo
- dynamic programming
- decentralized control
- learning process
- multiagent reinforcement learning