Featured
RL Weekly 44: Reinforcement Learning with Videos and Automatic Data Augmentation
In this issue, we look at using human demonstrations to help robot learn and automatically selecting data augmentation methods for RL.
Train Proximal Policy Optimization (PPO) with Swift for TensorFlow (S4TF)
We look at each component of Proximal Policy Optimization, and see how they can be translated to Swift for TensorFlow.
All Stories
MathCaptions: Reader-Friendly Equations
MathCaptions is a JavaScript library that allows you to highlight parts of equation that match the explanation.
Finding the Best Boomark Manager... For Me
With Google Summer of Code 2020 coming to a close, I describe my experience working with the TensorFlow team and share my advice for prospective...
RL Weekly 43: Revisiting Experience Replay, On-Policy Methods, and Rainbow
In this issue, we examine large scale experiments that illuminate the design decisions of various components of reinforcement learning.
Paper Unraveled: Revisiting Fundamentals of Experience Replay (Fedus et al., 2020)
Experience replay is central to off-policy algorithms in deep reinforcement learning (RL), but there remain significant gaps in our understanding. We therefore present a systematic...
Retrospective of Google Summer of Code 2020 with TensorFlow
With Google Summer of Code 2020 coming to a close, I describe my experience working with the TensorFlow team and share my advice for prospective...
Never miss an issue of RL Weekly from us, subscribe to our newsletter