doi.bio/matthias_plappert


Matthias Plappert

Matthias Plappert is a research scientist with interests in machine learning, robotics, reinforcement learning, and code synthesis. He is currently a Senior Research Advisor at DeepMind.

Education

Plappert received his Bachelor of Science from the Karlsruhe Institute of Technology, where he wrote his thesis on the "Classification of Human Whole-Body Motion using Hidden Markov Models." He later completed his Master's degree, with a thesis on "Parameter Space Noise for Exploration in Deep Reinforcement Learning."

Career

Plappert has worked with several notable organizations in the field of AI and machine learning. He was an intern at OpenAI, where he worked on projects such as "Learning Dexterous In-Hand Manipulation" and "Solving Rubik's Cube with a Robot Hand." He also contributed to the development of Codex, a GPT language model fine-tuned on publicly available code from GitHub, which powers GitHub Copilot.

Plappert has also been affiliated with the Karlsruhe Institute of Technology (KIT), where he collaborated with researchers like Tamim Asfour and Christian Mandery. Their work together includes publications on "Learning a bidirectional mapping between human whole-body motion and natural language using deep recurrent neural networks" and "The KIT Motion-Language Dataset."

In addition to his research, Plappert has presented at various symposiums and workshops, including the OpenAI Robotics Symposium in 2019 and NeurIPS 2018, where he presented on "Learning Dexterity." He has also developed tools such as Keras-RL, a deep reinforcement learning library, and PiBot, a simple robot platform based on a Raspberry Pi.

Notable Works

Youtube Videos

Youtube Title: OpenAI Spinning Up in Deep RL Workshop

Youtube Link: link

Youtube Channel Name: OpenAI

Youtube Channel Link: https://www.youtube.com/@OpenAI

OpenAI Spinning Up in Deep RL Workshop

Youtube Title: OpenAI Robotics Symposium 2019

Youtube Link: link

Youtube Channel Name: OpenAI

Youtube Channel Link: https://www.youtube.com/@OpenAI

OpenAI Robotics Symposium 2019

Youtube Title: Ingredients for Robotics Research

Youtube Link: link

Youtube Channel Name: OpenAI

Youtube Channel Link: https://www.youtube.com/@OpenAI

Ingredients for Robotics Research

Youtube Title: Bidirectional mapping between human whole-body motion and natural language using deep RNNs

Youtube Link: link

Youtube Channel Name: HumanoidRobots

Youtube Channel Link: https://www.youtube.com/@HumanoidRobots

Bidirectional mapping between human whole-body motion and natural language using deep RNNs

Youtube Title: DQN Cartpole

Youtube Link: link

Youtube Channel Name: Rowing0914

Youtube Channel Link: https://www.youtube.com/@Rowing-li6jt

DQN Cartpole

Youtube Title: How to Train a Robot Arm - A New Method

Youtube Link: link

Youtube Channel Name: Elliot Waite

Youtube Channel Link: https://www.youtube.com/@elliotwaite

How to Train a Robot Arm - A New Method

Youtube Title: Marcin Andrychowicz - Solving Rubik’s Cube with a Robot Hand

Youtube Link: link

Youtube Channel Name: ML in PL

Youtube Channel Link: https://www.youtube.com/@MLinPLAssociation

Marcin Andrychowicz - Solving Rubik’s Cube with a Robot Hand

Youtube Title: CVPR 2023 Paper Compilation - TUM Visual Computing Lab & Collaborators

Youtube Link: link

Youtube Channel Name: Matthias Niessner

Youtube Channel Link: https://www.youtube.com/@MatthiasNiessner

CVPR 2023 Paper Compilation - TUM Visual Computing Lab & Collaborators

Youtube Title: GPT5 INSANE New Model That SHOCKS The Entire World

Youtube Link: link

Youtube Channel Name: AI Academy

Youtube Channel Link: https://www.youtube.com/@aiacademy192

GPT5 INSANE New Model That SHOCKS The Entire World

Youtube Title: Why Robots Need to be Able to Say "No" | Matthias Scheutz | TEDxVienna

Youtube Link: link

Youtube Channel Name: TEDx Talks

Youtube Channel Link: https://www.youtube.com/@TEDx

Why Robots Need to be Able to Say "No" | Matthias Scheutz | TEDxVienna

Youtube Title: Solving Rubik's Cube with a Robotic Hand Explained!

Youtube Link: link

Youtube Channel Name: Connor Shorten

Youtube Channel Link: https://www.youtube.com/@connorshorten6311

Solving Rubik's Cube with a Robotic Hand Explained!

Youtube Title: All about OpenAI chatGPT how to register / Login,how to ask questions and save it .

Youtube Link: link

Youtube Channel Name: Online Learning Junction

Youtube Channel Link: https://www.youtube.com/@onlinelearningjunction6764

All about OpenAI chatGPT how to register / Login,how to ask questions and save it .

Youtube Title: Silviu Pitis on Generalizing O.O.D. using Counterfactual Data Augmentation | Toronto AIR Seminar

Youtube Link: link

Youtube Channel Name: AI Robotics Seminar - University of Toronto

Youtube Channel Link: https://www.youtube.com/@AIRoboticsSeminar-UofT

Silviu Pitis on Generalizing O.O.D. using Counterfactual Data Augmentation | Toronto AIR Seminar

Youtube Title: Deep Learning Salon by Weights & Biases

Youtube Link: link

Youtube Channel Name: Weights & Biases

Youtube Channel Link: https://www.youtube.com/@WeightsBiases

Deep Learning Salon by Weights & Biases

Youtube Title: Learning Dexterous Manipulation with a Robotic Hand with Alex Paino

Youtube Link: link

Youtube Channel Name: Weights & Biases

Youtube Channel Link: https://www.youtube.com/@WeightsBiases

Learning Dexterous Manipulation with a Robotic Hand with Alex Paino