deep-reinforcement-learning

KO | EN

gitlite — search

#javascript #hacktoberfest #ai #typescript #go #rust #deep-learning #linux #docker #macos #cli #pytorch #openai #open-source

deep-reinforcement-learning

(★ 58)

Programming Assignments and Lectures for UC Berkeley's CS 294: Deep Reinforcement Learning

deep-reinforcement-learning Latest Version Download

Download Latest Version (.zip)

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

![Cover](https://raw.githubusercontent.com/khanhnamle1994/deep-reinforcement-learning/master/Hopper_Backflips.gif)

Instructors: Sergey Levine, John Schulman, and Chelsea Finn.

This course will assume some familiarity with reinforcement learning, numerical optimization and machine learning. The course covers topics: Supervised learning and decision making; Basic reinforcement learning: Q-learning and policy gradients; Advanced model learning and prediction; Advanced deep reinforcement learning: trust region policy gradients, actor-critic methods, exploration; Open problems and research talks.

# Table of Contents
## Lectures

* Lecture 1: Introduction and course overview ([Video](https://www.youtube.com/watch?v=Q4kF8sfggoI&t=0s&list=PLkFD6_40KJIznC9CDbVTjAF2oyt8_VAe3&index=2)) ([Slides](https://github.com/khanhnamle1994/deep-reinforcement-learning/blob/master/Lectures/lecture_1_introduction.pdf))

* Lecture 2: Supervised learning and imitation ([Video](https://www.youtube.com/watch?v=C_LGsoe36I8&index=2&list=PLkFD6_40KJIznC9CDbVTjAF2oyt8_VAe3)) ([Slides](https://github.com/khanhnamle1994/deep-reinforcement-learning/blob/master/Lectures/lecture_2_behavior_cloning.pdf))

* Lecture 3: Reinforcement learning introduction ([Video](https://www.youtube.com/watch?v=PTbxa6GsTWc&index=3&list=PLkFD6_40KJIznC9CDbVTjAF2oyt8_VAe3)) ([Slides](https://github.com/khanhnamle1994/deep-reinforcement-learning/blob/master/Lectures/lecture_3_rl_intro.pdf))

* Lecture 4: Policy gradients introduction ([Video](https://www.youtube.com/watch?v=tWNpiNzWuO8&index=4&list=PLkFD6_40KJIznC9CDbVTjAF2oyt8_VAe3)) ([Slides](https://github.com/khanhnamle1994/deep-reinforcement-learning/blob/master/Lectures/lecture_4_policy_gradient.pdf))

* Lecture 5: Actor-critic introduction ([Video](https://www.youtube.com/watch?v=PpVhtJn-iZI&index=5&list=PLkFD6_40KJIznC9CDbVTjAF2oyt8_VAe3)) ([Slides](https://github.com/khanhnamle1994/deep-reinforcement-learning/blob/master/Lectures/lecture_5_actor_critic_pdf.pdf))

* Lecture 6: Value functions introduction ([Video](https://www.youtube.com/watch?v=k1vNh4rNYec&list=PLkFD6_40KJIznC9CDbVTjAF2oyt8_VAe3&index=6)) ([Slides](https://github.com/khanhnamle1994/deep-reinforcement-learning/blob/master/Lectures/lecture_6_value_functions.pdf))

* Lecture 7: Advanced Q-learning algorithms ([Video](https://www.youtube.com/watch?v=nZXC5OdDfs4&index=7&list=PLkFD6_40KJIznC9CDbVTjAF2oyt8_VAe3)) ([Slides](https://github.com/khanhnamle1994/deep-reinforcement-learning/blob/master/Lectures/lecture_7_advanced_q_learning.pdf))

* Lecture 8: Optimal control and planning ([Video](https://www.youtube.com/watch?v=EfgC7v5V608&list=PLkFD6_40KJIznC9CDbVTjAF2oyt8_VAe3&index=8)) ([Slides](https://github.com/khanhnamle1994/deep-reinforcement-learning/blob/master/Lectures/lecture_8_model_based_planning.pdf))

* Lecture 9: Learning dynamical systems from data ([Video](https://www.youtube.com/watch?v=yap_g0d7iBQ&index=9&list=PLkFD6_40KJIznC9CDbVTjAF2oyt8_VAe3)) ([Slides](https://github.com/khanhnamle1994/deep-reinforcement-learning/blob/master/Lectures/lecture_9_model_based_rl.pdf))

* Lecture 10: Learning policies by imitating optimal controllers ([Video](https://www.youtube.com/watch?v=AwdauFLan7M&list=PLkFD6_40KJIznC9CDbVTjAF2oyt8_VAe3&index=10)) ([Slides](https://github.com/khanhnamle1994/deep-reinforcement-learning/blob/master/Lectures/lecture_10_imitating_optimal_control.pdf))

* Guest Lecture: Advanced model learning and images ([Video](https://www.youtube.com/watch?v=vRkIwM4GktE&list=PLkFD6_40KJIznC9CDbVTjAF2oyt8_VAe3&index=11)) ([Slides](https://github.com/khanhnamle1994/deep-reinforcement-learning/blob/master/Lectures/guest_lecture_advanced_model_learning.pdf))

* Lecture 11: Connection between inference and control ([Video](https://www.youtube.com/watch?v=iOYiPhu5GEk&list=PLkFD6_40KJIznC9CDbVTjAF2oyt8_VAe3&index=12)) ([Slides](https://github.com/khanhnamle1994/deep-reinforcement-learning/blob/master/Lectures/lecture_11_control_and_inference.pdf))

* Lecture 12: Inverse reinforcement learning ([Video](https://www.youtube.com/watch?v=-3BcZwgmZLk&list=PLkFD6_40KJIznC9CDbVTjAF2oyt8_VAe3&index=13)) ([Slides](https://github.com/khanhnamle1994/deep-reinforcement-learning/blob/master/Lectures/lecture_12_inverse_reinforcement_learning.pdf))

* Lecture 13 (Part 1): Advanced policy gradients (natural gradient, importance sampling) ([Video](https://www.youtube.com/watch?v=ycCtmp4hcUs&list=PLkFD6_40KJIznC9CDbVTjAF2oyt8_VAe3&index=14)) ([Slides](https://github.com/khanhnamle1994/deep-reinforcement-learning/blob/master/Lectures/lecture_13_advanced_pg.pdf))

* Lecture 13 (Part 2): Exploration ([Video](https://www.youtube.com/watch?v=npi6B4VQ-7s&index=15&list=PLkFD6_40KJIznC9CDbVTjAF2oyt8_VAe3)) ([Slides](https://github.com/khanhnamle1994/deep-reinforcement-learning/blob/master/Lectures/lecture_13_exploration.pdf))

* Lecture 14: Exploration (part 2) and transfer learning ([Video](https://www.youtube.com/watch?v=0WbVUvKJpg4&list=PLkFD6_40KJIznC9CDbVTjAF2oyt8_VAe3&index=16)) ([Slides](https://github.com/khanhnamle1994/deep-reinforcement-learning/blob/master/Lectures/lecture_14_transfer.pdf))

* Lecture 15: Multi-task learning and transfer ([Video](https://www.youtube.com/watch?v=UqSx23W9RYE&index=17&list=PLkFD6_40KJIznC9CDbVTjAF2oyt8_VAe3)) ([Slides](https://github.com/khanhnamle1994/deep-reinforcement-learning/blob/master/Lectures/lecture_15_multi_task_learning.pdf))

* Lecture 16: Meta-learning and parallelism ([Video](https://www.youtube.com/watch?v=Xe9bktyYB34&index=18&list=PLkFD6_40KJIznC9CDbVTjAF2oyt8_VAe3)) ([Slides](https://github.com/khanhnamle1994/deep-reinforcement-learning/blob/master/Lectures/lecture_16_meta_learning.pdf))

* Lecture 17: Advanced imitation learning and open problems ([Video](https://www.youtube.com/watch?v=mc-DtbhhiKA&list=PLkFD6_40KJIznC9CDbVTjAF2oyt8_VAe3&index=19)) ([Slides](https://github.com/khanhnamle1994/deep-reinforcement-learning/blob/master/Lectures/lecture_17_challenges.pdf))

## Assignments

* Homework 1: Imitation Learning ([Problem](https://github.com/khanhnamle1994/deep-reinforcement-learning/blob/master/Assignments/hw1fall2017.pdf)) ([Solution](https://github.com/khanhnamle1994/deep-reinforcement-learning/tree/master/hw1))
* Homework 2: Policy Gradients ([Problem](https://github.com/khanhnamle1994/deep-reinforcement-learning/blob/master/Assignments/hw2_final.pdf)) ([Solution](https://github.com/khanhnamle1994/deep-reinforcement-learning/tree/master/hw2))
* Homework 3: Q-Learning on Atari ([Problem](https://github.com/khanhnamle1994/deep-reinforcement-learning/blob/master/Assignments/hw3_final.pdf)) ([Solution](https://github.com/khanhnamle1994/deep-reinforcement-learning/tree/master/hw3))
* Homework 4: Model-Based RL ([Problem](https://github.com/khanhnamle1994/deep-reinforcement-learning/blob/master/Assignments/hw4_final.pdf)) ([Solution](https://github.com/khanhnamle1994/deep-reinforcement-learning/tree/master/hw4))

deep-reinforcement-learning

deep-reinforcement-learning Latest Version Download

Today's picks

Was this content helpful?

Recent Feedback

deep-reinforcement-learning

deep-reinforcement-learning Latest Version Download

Today's picks

Was this content helpful?

Recent Feedback

Download README