-
Paper Notes -- Consistency Models
1/18/2025Notes for this paper
-
Paper Notes -- Improved Techniques for Training Consistency Models
1/13/2025Notes for this paper
-
How Log-Likelihood Helps Approximate the True Data Distribution?
9/19/2024Some thoughts about why we use log-likelihood as the loss function when we approximate the true data distribution.
-
Multi-Arm Bandits
9/18/2024Note for Chapter 2 of RL: an introduction
-
Paper Notes - Diffusion Policies creating a Trust Region for Offline Reinforcement Learning
9/16/2024This paper proposed to train a one-step policy guided by a diffusion model via a trust region loss, enabling fast inference without iterative sampling.
-
Paper Notes - Efficient Diffusion Policies for Offline Reinforcement Learning
9/12/2024Notes for this paper.
-
Paper Notes - Diffusion Policies as an Expressive Policy Class for Offline Reinforcement Learning
9/10/2024Notes for this paper.
No posts found matching your search.