Search Results for author:
Found 3 papers, 0 papers with code
Fighting Uncertainty with Gradients: Offline Reinforcement Learning via Diffusion Score Matching
However, in order to apply them effectively in offline optimization paradigms such as offline Reinforcement Learning (RL) or Imitation Learning (IL), we require a more careful consideration of how uncertainty estimation interplays with first-order methods that attempt to minimize them.
Do Differentiable Simulators Give Better Policy Gradients?
Differentiable simulators promise faster computation time for reinforcement learning by replacing zeroth-order gradient estimates of a stochastic objective with an estimate based on first-order gradients.
The Surprising Effectiveness of Linear Models for Visual Foresight in Object Pile Manipulation
In this paper, we tackle the problem of pushing piles of small objects into a desired target set using visual feedback.
Robotics
