Diffusion Policies for Out-of-Distribution Generalization in Offline Reinforcement Learning.
Suzan Ece AdaErhan ÖztopEmre UgurPublished in: CoRR (2023)
Keyphrases
- reinforcement learning
- optimal policy
- policy search
- markov decision process
- function approximation
- real time
- markov decision processes
- reward function
- data distribution
- anisotropic diffusion
- hierarchical reinforcement learning
- reinforcement learning algorithms
- spatial distribution
- information diffusion
- multi agent systems
- learning agent
- decentralized control
- multi agent
- machine learning