Search Results for author:
Found 4 papers, 1 papers with code
Exploring validation metrics for offline model-based optimisation with diffusion models
Measuring the mean reward of generated candidates over this approximation is one such `validation metric', whereas we are interested in a more fundamental question which is finding which validation metrics correlate the most with the ground truth.
Bridging the Gap Between Target Networks and Functional Regularization
However, learning the value function via bootstrapping often leads to unstable training due to fast-changing target values.
Implicit Offline Reinforcement Learning via Supervised Learning
Despite the benefits of using implicit models to learn robotic skills via BC, offline RL via Supervised Learning algorithms have been limited to explicit models.
Probabilistic Planning with Sequential Monte Carlo methods
In this work, we propose a novel formulation of planning which views it as a probabilistic inference problem over future optimal trajectories.
