Louis Kirsch

Improving Generalization in Meta Reinforcement Learning using Learned Objectives

2019 · arXiv (Cornell University)

Biological evolution has distilled the experiences of many learners into the general learning algorithms of humans. Our novel meta reinforcement learning algorithm MetaGenRL is inspired by this process. MetaGenRL distills the experiences of many complex …

Meta Learning Backpropagation And Improving It

2020 · arXiv (Cornell University)

Many concepts have been proposed for meta learning with neural networks (NNs), e.g., NNs that learn to reprogram fast weights, Hebbian plasticity, learned learning rules, and meta recurrent NNs. Our Variable Shared Meta Learning (VSML) …

The Benefits of Model-Based Generalization in Reinforcement Learning

2022 · arXiv (Cornell University)

Model-Based Reinforcement Learning (RL) is widely believed to have the potential to improve sample efficiency by allowing an agent to synthesize large amounts of imagined experience. Experience Replay (ER) can be considered a simple kind …