UC-Berkeley-CS-294-Deep-RL

KO | EN

gitlite — search

#python #react #typescript #llm #android #linux #docker #windows #cli #awesome-list #vue #pytorch #mcp #ios

UC-Berkeley-CS-294-Deep-RL

(★ 24)

Implementation of Deep RL Algorithms for UC Berkeley's CS 294-112 (Fall 2018): Deep Reinforcement Learning

UC-Berkeley-CS-294-Deep-RL 최신버젼 다운로드

최종 버전 다운로드 (.zip)

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

# CS 294 at UC Berkeley: Deep Reinforcement Learning

This repo includes my solutions to the assigments of the UC Berkeley Deep Reinforcement Learning course offered in Fall 2018, taught by Sergey Levine.

Course URL: http://rail.eecs.berkeley.edu/deeprlcourse/

Course GitHub: https://github.com/berkeleydeeprlcourse/homework

I would like to thank the instructor and the TAs for making this wonderful course.

## Code structure
- `./hw1/`: contains code for the implementation of **imitation learning**, including direct **behavior cloning** and the **DAgger** algorithm. See my report for this homework [here](./hw1/README.md). 
- `./hw2/`: contains code for the implementation of **policy gradient** and its variants, including **variance reduction methods**. See my report for this homework [here](./hw2/README.md). Below you can see some cool videos showing the comparison between the learning agent before and after training using the policy gradient.

|  |Before training  |	After training 	
|--|--|--|	
| CartPole | <img src="./videos/CartPole-wo-learning.gif" height="300px" width="300px" > | <img src="./videos/CartPole-w-learning.gif" height="300px" width="300px" > |
| LunarLander | <img src="./videos/LunarLander-wo-learning.gif" height="300px" width="300px" > | <img src="./videos/LunarLander-w-learning.gif" height="300px" width="300px" > |
| InvertedPendulum | <img src="./videos/InvertedPendulum-wo-learning.gif" height="300px" width="300px" > | <img src="./videos/InvertedPendulum-w-learning.gif" height="300px" width="300px" > |
| HalfCheetah | <img src="./videos/HalfCheetah-wo-learning.gif" height="300px" width="300px" > | <img src="./videos/HalfCheetah-w-learning.gif" height="300px" width="300px" > |

- `./hw3/`: contains code for the implementation of **Deep Q-Learning** and **Actor-Critic**. See my report for this homework [here](./hw3/README.md). Below you can see some cool videos showing the comparison between the learning agent before and after training using Deep Q-Learning.

`Pong Atari (green pedal is controlled by our learning agent) `

- `./hw4/`: contains code for the implementation of an algorithm for the **model-based reinforcement learning (MBRL)**. See my report for this homework [here](./hw4/README.md).

UC-Berkeley-CS-294-Deep-RL

UC-Berkeley-CS-294-Deep-RL 최신버젼 다운로드

오늘의 추천 프로젝트

Was this content helpful?

Recent Feedback

UC-Berkeley-CS-294-Deep-RL

UC-Berkeley-CS-294-Deep-RL 최신버젼 다운로드

오늘의 추천 프로젝트

Was this content helpful?

Recent Feedback

Download README