Marcin Andrychowicz - Solving Rubik’s Cube with a Robot Hand
Recorded at the ML in PL 2019 Conference, the University of Warsaw, 22-24 November 2019.
Marcin Andrychowicz (OpenAI/Google Brain Zurich)
The second part of the talk is available at https://youtu.be/Va5dIxejqx0.
Slides available at http://docs.mlinpl.org/conference/2019/slides/marcin_andrychowicz_mlinpl2019.pdf
Abstract:
I will describe how we can use Reinforcement Learning (RL) to train control policies for physical robots. I'll discuss the issue of transferring control policies from a simulator to the real world and present the technique of Automatic Domain Randomization, which relies on randomizing the appearance as well as the dynamics of the simulated environment and automatically generates a distribution over randomized environments of ever-increasing difficulty. In particular, I'll focus on the problem of dexterous in-hand manipulation with a humanoid hand (https://openai.com/blog/solving-rubiks-cube/).
Видео Marcin Andrychowicz - Solving Rubik’s Cube with a Robot Hand канала ML in PL
Marcin Andrychowicz (OpenAI/Google Brain Zurich)
The second part of the talk is available at https://youtu.be/Va5dIxejqx0.
Slides available at http://docs.mlinpl.org/conference/2019/slides/marcin_andrychowicz_mlinpl2019.pdf
Abstract:
I will describe how we can use Reinforcement Learning (RL) to train control policies for physical robots. I'll discuss the issue of transferring control policies from a simulator to the real world and present the technique of Automatic Domain Randomization, which relies on randomizing the appearance as well as the dynamics of the simulated environment and automatically generates a distribution over randomized environments of ever-increasing difficulty. In particular, I'll focus on the problem of dexterous in-hand manipulation with a humanoid hand (https://openai.com/blog/solving-rubiks-cube/).
Видео Marcin Andrychowicz - Solving Rubik’s Cube with a Robot Hand канала ML in PL
Показать
Комментарии отсутствуют
Информация о видео
Другие видео канала
Rafał Pilarczyk: Is Artificial Intelligence a threat to musicians? – Music generation techniques
Philippe Preux - Bits of Reinforcement Learning | ML in PL 23
B. Ludwiczuk, K. Jasinska-Kobus (Allegro) - Batch construction strategies in deep metric learning
Adam Paszke: PyTorch 1.0: now and in the future
Adam Podraza: Applied time series forecasting using machine learning
Gül Varol - Learning human body representations from visual data
David Haber - Opportunities and Challenges when Building AI for Autonomous Flight
Adam Gonczarek (Alphamoon) – Intelligent Document Processing
Jonasz Pamuła (RTB House) – ML Challenges in cookieless world
João Henriques - Mapping environments with deep networks and spatial memories
Krzysztof Geras (NYU): "Towards Solving Breast Cancer Screening Diagnosis with Deep Learning"
Stanisław Jastrzębski - Deep Learning in the Light of the Simplicity Bias | MLSS Kraków 2023
How to learn classifier chains using positive-unlabelled multi-label data? | ML in PL 22
Yoshua Bengio – Cognitively-inspired inductive biases for higher-level cognition
Tomasz Grel (Nvidia): Faster Deep Learning with mixed precision and multiple GPUs
Panel Discussion – Women in ML
Michał Jamroż - Class fitting in residual convolutional networks | ML in PL 23
Sebastian Cygert - Toward continually learning models | ML in PL 23
Barbara Rychalska - Neural Machine Translation: achievements, challenges and the way forward
Stanisław Jastrzębski - Gradient Alignment: When Deep Networks Work, and When They Don't