Published Feb 28, 2021

#045 Microsoft's Platform for Reinforcement Learning (Bonsai)

Explore the transformative role of simulation in reinforcement learning through Microsoft's Project Bonsai, as it simplifies complex processes and blends human expertise with AI to optimize problem-solving and model robustness.

Episode Highlights

Topics covered

Episode Highlights

Related Episodes

#114 - Secrets of Deep Reinforcement Learning (Minqi Jiang)
Answers 383 questions
#65 Prof. PEDRO DOMINGOS [Unplugged]
Answers 383 questions
Robert Lange on NN Pruning and Collective Intelligence
Answers 383 questions
#032- Simon Kornblith / GoogleAI - SimCLR and Paper Haul!
Answers 383 questions
Explainability, Reasoning, Priors and GPT-3
Answers 383 questions
#046 The Great ML Stagnation (Mark Saroufim and Dr. Mathew Salvaris)
Answers 383 questions
ICLR 2020: Yoshua Bengio and the Nature of Consciousness
Answers 383 questions
Kernels!
Answers 383 questions
#035 Christmas Community Edition!
Answers 383 questions
Understanding Deep Learning - Prof. SIMON PRINCE [STAFF FAVOURITE]
Answers 383 questions
#53 Quantum Natural Language Processing - Prof. Bob Coecke (Oxford)
Answers 383 questions
#94 - ALAN CHAN - AI Alignment and Governance #NEURIPS
Answers 383 questions
#54 Gary Marcus and Luis Lamb - Neurosymbolic models
Answers 383 questions
Can we build a generalist agent? Dr. Minqi Jiang and Dr. Marc Rigter
Answers 383 questions
#86 - Prof. YANN LECUN and Dr. RANDALL BALESTRIERO - SSL, Data Augmentation, Reward isn't enough [NEURIPS2022]
Answers 383 questions

Dexa/Machine Learning Street Talk (MLST)

#045 Microsoft's Platform for Reinforcement Learning (Bonsai)

Topics covered

Popular Clips

Machine Teaching Oracles

Machine Teaching Insights

Reinforcement Learning Efficiency

New Software Paradigm

Industrial Process Optimization

Machine Teaching Benefits

Deep Reinforcement Learning Insights

Machine Teaching Insights

Machine Teaching Insights

Hybrid Predictive Architectures

Reinforcement Learning Abstraction

Advancing Machine Learning

Machine Teaching Evolution

Complex Dynamics in Reinforcement Learning

Episode Highlights

Simulation and Modeling

Machine Teaching

Reinforcement Learning

Related Episodes

#114 - Secrets of Deep Reinforcement Learning (Minqi Jiang)

#65 Prof. PEDRO DOMINGOS [Unplugged]

Robert Lange on NN Pruning and Collective Intelligence

#032- Simon Kornblith / GoogleAI - SimCLR and Paper Haul!

Explainability, Reasoning, Priors and GPT-3

#046 The Great ML Stagnation (Mark Saroufim and Dr. Mathew Salvaris)

ICLR 2020: Yoshua Bengio and the Nature of Consciousness

Kernels!

#035 Christmas Community Edition!

Understanding Deep Learning - Prof. SIMON PRINCE [STAFF FAVOURITE]

#53 Quantum Natural Language Processing - Prof. Bob Coecke (Oxford)

#94 - ALAN CHAN - AI Alignment and Governance #NEURIPS

#54 Gary Marcus and Luis Lamb - Neurosymbolic models

Can we build a generalist agent? Dr. Minqi Jiang and Dr. Marc Rigter

#86 - Prof. YANN LECUN and Dr. RANDALL BALESTRIERO - SSL, Data Augmentation, Reward isn't enough [NEURIPS2022]

#045 Microsoft's Platform for Reinforcement Learning (Bonsai)

Topics covered

Popular Clips

Episode Highlights

Simulation and Modeling

Machine Teaching

Reinforcement LearningTim Scarfe explores the challenges and innovations in reinforcement learning, focusing on Microsoft's Project Bonsai. He discusses how Bonsai aims to simplify complex RL processes, making them more accessible and efficient for traditional software engineering.

Reinforcement Learning

Related Episodes