Subscribe: iTunes / Google Play / Spotify / RSS
Abhishek, a member of the BAIR Lab, joined us to talk about his recent robotics and reinforcement learning research and interests, which focus on applying RL to real-world robotics applications. We explore the concept of reward supervision, and how to get robots to learn these reward functions from videos, and the rationale behind supervised experts in these experiments. We also discuss the use of simulation for experiments, data collection, and the path to scalable robotic learning. Finally, we discuss gradient surgery vs gradient sledgehammering, and his ecological RL paper, which focuses on the “phenomena that exist in the real world” and how humans and robotics systems interface in those situations.Connect with Abhishek!
Resources
- Paper: Gradient surgery for multi-task learning
- Paper: Unsupervised meta-learning for reinforcement learning
- Paper: Diversity is all you need
- Paper: Ecological reinforcement learning
- Paper: Imitation from Observation
- Paper: Ingredients of Real-World Reinforcement Learning
- Reinforcement Learning Deep Dive with Pieter Abbeel
- Advances in Reinforcement Learning with Sergey Levine
- Deep Robotic Learning with Sergey Levine
- Trends in Reinforcement Learning with Chelsea Finn
- Robotic Perception and Control with Chelsea Finn
- Training Large-Scale Deep Nets with RL with Nando de Freitas
Join Forces!
- Check out our TWIML Presents: series page!
- Register for the TWIML Newsletter
- Check out the official TWIMLcon:AI Platform video packages here!
- Download our latest eBook, The Definitive Guide to AI Platforms!
Leave a Reply