Conquering OpenAI Retro Contest 2: Demystifying Rainbow Baseline

0 About OpenAI baselines

[Paper Notes 1]QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulation

1 Summary

This paper proposes a novel Deep Reinforcement Learning algorithm QT-Opt for vision-based robotic manipulation problem…

Robot Learning Restarting

After more than one year’s exploration on Deep Reinforcement Learning, Meta Learning, Few-Shot Learning, I…

Welcome

Artificial General Intelligence is coming!

[Paper Notes 3] Sim-to-Real Reinforcement Learning for Deformable Object Manipulation

Conquering OpenAI Retro Contest 3: A Collection of Related Papers

OpenAI Retro Contest is a new kind of Reinforcement Learning benchmark targeting on Transfer Learning, Multi-Task Learning and Meta Learning. In this blog, I make a collection of related papers, so that we can dig…