Chapter
Exploring Reinforcement Learning
44:12 - 53:49 (09:37)
This podcast episode discusses the concepts of reinforcement learning, including policy based, model-based, on policy and off policy. The speakers consider the potential for reinforcement learning to solve a broad range of AI problems in the future.
Clips
Reinforcement learning is a powerful tool that encapsulates a range of decision-making problems within AI.
44:12 - 47:20 (03:08)
Reinforcement Learning
Summary
Reinforcement learning is a powerful tool that encapsulates a range of decision-making problems within AI. It is the modern incarnation of learning-based control and has a broad potential to tackle numerous problems in AI.
ChapterExploring Reinforcement Learning
Episode#108 – Sergey Levine: Robotics and Machine Learning
PodcastLex Fridman Podcast
The speaker explains the different types of reinforcement learning, policy-based, model-based, on/off-policy, and value-based, and why it's difficult to apply reinforcement learning in most settings today.
47:20 - 53:49 (06:29)
reinforcement learning
Summary
The speaker explains the different types of reinforcement learning, policy-based, model-based, on/off-policy, and value-based, and why it's difficult to apply reinforcement learning in most settings today.