Learning Dexterous In-Hand Manipulation.

By OpenAI. 2018

86 citations recorded by the source corpus.

Subfields: Reinforcement Learning, Robotics & Control

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Reinforcement Learning

1. Sergey Levine
2. Gabriel Dulac-Arnold
3. Ruslan Salakhutdinov
4. Aviral Kumar
5. Chelsea Finn
6. Cosmin Paduraru
7. Avi Singh
8. Pieter Abbeel

In Robotics & Control

1. Aviral Kumar
2. Avi Singh
3. Ruslan Salakhutdinov
4. Gabriel Dulac-Arnold
5. Sergey Levine
6. Albert Yu
7. Brandon Houghton
8. Cayden R. Codel

Citations in the corpus

• An empirical investigation of the challenges of real-world reinforcement learning (2020, methodology): “RL methods have been shown to be effective on a large set of simulated environments [Mnih et al. 2015; Silver et al. 2016; Lillicrap et al. 2015; OpenAI 2018; Tessler et al. 2016], but uptake in real-world problems has been much slower.”
• COG: Connecting New Skills to Past Experience with Offline Reinforcement Learning (2020, methodology): “d on a real world low-cost robotic arm. 2 Related Work Robotic RL. RL has been applied to a wide variety of robotic manipulation tasks, including grasping objects [11,12], in-hand object manipulation [13,14,15,16], pouring fluids [17], door opening [18, 2 19], and manipulating cloth [20,21]. Most of ”
• MineRL: A Large-Scale Dataset of Minecraft Demonstrations (2019, methodology): “Our system renders demonstrations from packet-level data, so the game state and rendering parameters can be changed. play [ OpenAI, 2018 ] , AlphaGoZero uses 4.9 million games of self-play in Go [ Silver et al. , 2017 ] , and AlphaStar uses 200 years of Starcraft II gameplay [ DeepMind, 2018 ] .”