Extracting Reward Functions from Diffusion Models.
Felipe NutiTim FranzmeyerJoão F. HenriquesPublished in: CoRR (2023)
Keyphrases
- diffusion models
- reward function
- diffusion model
- information diffusion
- social networks
- reinforcement learning
- markov decision processes
- state space
- optimal policy
- influence maximization
- multiple agents
- transition probabilities
- inverse reinforcement learning
- generative model
- state variables
- greedy algorithm
- dynamic programming
- machine learning
- maximum entropy
- semi supervised
- probabilistic model
- multi agent