Reasoning with Latent Diffusion in Offline Reinforcement Learning.
Siddarth VenkatramanShivesh KhaitanRavi Tej AkellaJohn DolanJeff SchneiderGlen BersethPublished in: ICLR (2024)
Keyphrases
- reinforcement learning
- function approximation
- anisotropic diffusion
- real time
- reinforcement learning algorithms
- knowledge base
- model based reasoning
- optimal policy
- latent variables
- learning algorithm
- multi agent
- knowledge representation
- reasoning systems
- reasoning process
- machine learning
- diffusion process
- information diffusion
- legal reasoning
- learning problems
- case based reasoning
- policy search
- robotic control