|TREND||DATASET||BEST METHOD||PAPER TITLE||PAPER||CODE||COMPARE|
Therefore, if the aim of these methods is to enable faster acquisition of entirely new behaviors, we must evaluate them on task distributions that are sufficiently broad to enable generalization to new behaviors.
SOTA for Meta-Learning on ML10
In our approach, we perform online probabilistic filtering of latent task variables to infer how to solve a new task from small amounts of experience.
We consider the problem of exploration in meta reinforcement learning.
Although reinforcement learning methods can achieve impressive results in simulation, the real world presents two major challenges: generating samples is exceedingly expensive, and unexpected perturbations or unseen situations cause proficient but specialized policies to fail at test time.
Autoregressive generative models consistently achieve the best results in density estimation tasks involving high dimensional data, such as images or audio.
#2 best model for Image Generation on CIFAR-10 (NLL Test metric)
Despite significant progress, deep reinforcement learning (RL) suffers from data-inefficiency and limited generalization.