MIT 6.S191: Reinforcement Learning

MIT Introduction to Deep Learning 6.S191: Lecture 5
Deep Reinforcement Learning
Lecturer: Alexander Amini
2024 Edition

Lecture Outline:
0:00 - Introduction
2:20 - Classes of learning problems
6:33 - Definitions
12:30 - The Q function
17:29 - Deeper into the Q function
23:12 - Deep Q Networks
30:36 - Atari results and limitations
34:24 - Policy learning algorithms
39:31 - Discrete vs continuous actions
43:21 - Training policy gradients
49:10 - RL in real life
51:33 - VISTA simulator
53:24 - AlphaGo and AlphaZero and MuZero
58:58 - Summary

Subscribe to stay up to date with new deep learning lectures at MIT, or follow us @MITDeepLearning on Twitter and Instagram to stay fully-connected!!

[izharulhaq]

One of the best intro to RL. Recommended to every student interested in this field to watch this amazing lecture. I have just completed it at 1:40 AM...Now waiting for Actor-Critic Type RL Agent to be released soon...Thanks and Good night.

[visheshphutela]

Babe wake up new 6.S191 lecture just dropped

[artukikemty]

Amazing intro to the subject. Since it is interrelated to control theory it is mandatory to have a good back ground on control theory such as state space models and optimal control

[gamalieliissacnyambacha]

I'm curious to listen to this lecture. I need more concepts to apply in my Thesis. I'm looking forward to seeing this happen soon.

[hrishabhg]

Lovely lecture.❤

Self driving car is a dynamic environment as compared to Gaming environment. It may be mentioned.

[Asif-fpgy]

Awesome job. Only curious if someone can explain how was the target part of the loss function computed at 26:40?

[Crashrapescrypto]

can you advise for my startup, we applied for YC, we want to setup up indian team and RLHF as well as using SIMPO to agentify the hospital system and remove the inefficiences faced in the current hospital systems. im an aussie coming to america. we have hardware as well, been in guangzhou for the last 6 weeks finding the best containers and cameras triend to train for guaging container volume for measuring stock remaining.

[melvinkuriakose]

10:30 equation for total reward should be summation of rewards from t=0 to t=t, right? But in equation its from t to infinity...why?

[artukikemty]

Transformers can be used as a direct replacement for DRL since it can process sequences as well. There is an article in medium related to this alternative.

[wbwufuq]

Hi, when i tried to run the modeling building part of lab 1, the line "tf.keras.layers.Embedding(vocab_size, embedding_dim, batch_input_shape=[batch_size, None]), " does not work, and the error says batch_input_shape is an unrecognized keyword argument to Embeddings, has anyone else encountered this problem? I looked up the tf.keras.Embeddings documentation and couldnt' find anything to replace it...What did you guys to solve it? Thanks!

[christianrink]

Can one conclude from the AlphaGo vs. AlphaZero showcase, that the bottleneck of "achieving" AGI/ASI, are we humans and the ethical/safety restrictions we have set?

[TheNewton]

Please repeat questions, question askers audio is blown out or intelligible.
Some of the questions manage to be in the captions others but not all.
The professors mic is perfect however with a great mix one of the few series where you don't have to be max volume all the time.

[ikpesuemmanuel]

Is there an application of reinforcement learning for subsurface reservoir simulation?

[ltvwryx]

Kenchin kokoro no.tabi.Study of the waste.