Videos

An introduction to Reinforcement Learning



Arxiv Insights

This episode gives a general introduction into the field of Reinforcement Learning:
– High level description of the field
– Policy gradients
– Biggest challenges (sparse rewards, reward shaping, …)

This video forms the basis for a series on RL where I will dive much deeper into technical details of state-of-the-art methods for RL.

Links:
– “Pong from Pixels – Karpathy”: http://karpathy.github.io/2016/05/31/rl/
– Concept networks for grasp & stack (Paper with heavy reward shaping): https://arxiv.org/abs/1709.06977

If you enjoy my videos, all support is super welcome!
https://www.patreon.com/ArxivInsights

Source

Similar Posts

38 thoughts on “An introduction to Reinforcement Learning
  1. Great video!!!! Explained exceptionally, liked other videos as well from your channel. Would love to see more stuff related to AI/DL or RL. Thanks in advance. Keep up the good work….

  2. your videos are some of the best explanations I've found for a lot of these very advanced subjects. I suspect your viewer count is going to jump very quickly. keep it up.

  3. Rewards and Reinforcements need clarification. A reward is focused on a result, and a reinforcement is focused on behavior. Sometimes the difference is very subtle and hence the confusion, but the outcome is significantly different.

  4. I've to submit a report on this topic 2 days from now. I'm a CS student of first semester and this was really difficult for me to understand. Can anyone help me ?

  5. When I was a psychology student when trained chickens using reinforcement training with reward shaping. However it was a form supervised training in reality

  6. Nope, the media doesnt focus on the negative sides of AI because they fear what they cant understand. We do it (I am a journalist) because it bad news sell more than good news.

  7. Very nice episode! One thing that struck me about your suggestion that without Reward Shaping, the auto-learning of the 2600 games would be intractable: even for a human, this would be extremely difficult – we succeed with new, undocumented games because they often have similar sub-components and sub-goals that we already know from other games (or life). But I'm sure you could easily construct a game which would be impossible for a human to learn without any hints, while still having the same overall complexity.

Comments are closed.

WP2Social Auto Publish Powered By : XYZScripts.com