Wei Wei, a Developer Advocate for TensorFlow, kicks off a new series on reinforcement learning where we explore how you can leverage TensorFlow Agents to build your own reinforcement learning agents.
Wei explains how reinforcement learning can be used to train agents to make the best decisions when performing actions in environments to maximize rewards.

Resources:
Reinforcement Learning Lecture Series 2021 (DeepMind x UCL) → https://goo.gle/3B6td3x

Introduction to Reinforcement Learning → https://goo.gle/3rwDWAV

Chip Design with Deep Reinforcement Learning → https://goo.gle/3uC9veH

Quickly Training Game-Playing Agents with Machine Learning → https://goo.gle/3gsCx8v

Leveraging Machine Learning for Game Development → https://goo.gle/3rAt7OB

OpenAI Gym → https://goo.gle/3srq5Ly

Github → https://goo.gle/3B6OPfW

Chapters:
00:00 Series introduction
00:55 Reinforcement learning example
01:30 What is reinforcement learning
02:24 Supervised learning vs. reinforcement learning
03:44 Taxonomy
05:13 Reinforcement learning applications
06:34 Training environments
08:13 References and summary

Watch more Reinforcement learning with TensorFlow Agents episodes → https://goo.gle/reinforcement-learning
Subscribe to TensorFlow → https://goo.gle/TensorFlow
Ask your questions on the TF Forum → https://goo.gle/discuss_tensorflow

#TensorFlow #MachineLearning #ML

product: TensorFlow - General; fullname: Wei Wei;