Continuous control and Actor-Learner API (Reinforcement learning with TensorFlow Agents) скачать в хорошем качестве

Continuous control and Actor-Learner API (Reinforcement learning with TensorFlow Agents)

Wei Wei, a Developer Advocate for TensorFlow, discusses continuous and discrete control, and walks through how to use the Minitaur environment to train a 4-legged robot to walk with the Actor-Learner API. Resources: SAC minitaur with the Actor-Learner API Tutorial → https://goo.gle/3oAa9FF TF Agents SAC example → https://goo.gle/35OzF3u TF Agents distributed training → https://goo.gle/3rzYj06 TensorFlow actor-critic tutorial → https://goo.gle/3HFckiN Chapters: 00:00 Introduction 00:27 SAC Agent 02:01 The minitaur environment 03:20 Minitaur training tutorial 07:05 TF-Agents distributed collection 07:49 Distributed architecture 08:30 Summary and resources 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;