From 72bc3cde1682c3740c4d974655041e94da227159 Mon Sep 17 00:00:00 2001 From: Aditya Vivekanand <142730385+adityavivekanand@users.noreply.github.com> Date: Wed, 12 Jun 2024 15:33:34 +0530 Subject: [PATCH 1/4] Create GymMaster.md GymMaster PR --- _projects/GymMaster.md | 36 ++++++++++++++++++++++++++++++++++++ 1 file changed, 36 insertions(+) create mode 100644 _projects/GymMaster.md diff --git a/_projects/GymMaster.md b/_projects/GymMaster.md new file mode 100644 index 0000000..1b33d83 --- /dev/null +++ b/_projects/GymMaster.md @@ -0,0 +1,36 @@ +--- +Layout: Page +Title: GymMaster +Description: Project to gain a deep understanding of Reinforcement Learning (RL) by systematically exploring and solving various OpenAI Gym environments. +--- + +| Project Domains | Mentors | Project Difficulty | +| --------------------------------------------------------- | ----------- | ------------------ | +| Reinforcement learning, OpenAI Gym, TenserFlow/ PyTorch, ML basics | Aditya Vivekanand | Medium to Hard | + +
+ +### Project Description + +This project involves building a solid theoretical foundation in RL concepts, implementing key algorithms like Dynamic Programming, Monte Carlo Methods and Policy Gradient Methods, and applying them to different tasks. +By experimenting with advanced techniques such as Double DQN and Actor-Critic methods, you will optimize agent performance and analyze results. +Comprehensive documentation and evaluation will enhance learning and provide insights for future applications, making this project a stepping stone to mastering RL. + +### Pre-requisites + +- Basic Python Programming -> [Python One-Shot by FreeCodeCamp](https://www.youtube.com/watch?v=rfscVS0vtbw) + +- Conceptual understanding of Reinforcement Learning -> [Playlist on basics of RL](https://www.youtube.com/watch?v=JgvyzIkgxF0) + +> It is recommended that candidates interested in this project go through the above resources. This will give you an advantage over others during interview for this project. + +### References + +- [OpenAI Gym Document](https://www.gymlibrary.dev/content/basic_usage/) +- [Sutton and Barto](https://www.google.co.in/books/edition/Reinforcement_Learning_second_edition/uWV0DwAAQBAJ?hl=en&gbpv=1&printsec=frontcover) + +### Mentor + +Aditya Vivekanand - avivekanand_b22@et.vjti.ac.in + +> If you have any doubts regarding this project or any difficulty in understanding the pre-requisites videos you reach out to the mentor. From eee299ee5b8951b21f9ab4b833ecf51b15be922f Mon Sep 17 00:00:00 2001 From: Aditya Vivekanand <142730385+adityavivekanand@users.noreply.github.com> Date: Wed, 12 Jun 2024 15:59:32 +0530 Subject: [PATCH 2/4] Create GymMaster.html GymMaster Site --- _site/projects/GymMaster/GymMaster.html | 296 ++++++++++++++++++++++++ 1 file changed, 296 insertions(+) create mode 100644 _site/projects/GymMaster/GymMaster.html diff --git a/_site/projects/GymMaster/GymMaster.html b/_site/projects/GymMaster/GymMaster.html new file mode 100644 index 0000000..2dd0fce --- /dev/null +++ b/_site/projects/GymMaster/GymMaster.html @@ -0,0 +1,296 @@ + + + + + + + + + + + + + GymMaster | Eklavya 2024 + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
+ + + + + + +
+ +
+ +
+ + + +
+ + +
+ +
+

GymMaster

+

GymMaster is a project to gain a deep understanding of reinforcement learning (RL) by systematically exploring and solving various OpenAI Gym environments.

+
+ +
+ + + + + + + + + + + + + + + +
Project DomainsMentorsProject Difficulty
Reinforcement learning, OpenAI Gym, TenserFlow/ PyTorch, Machine LearningAditya VivekanandMedium - Hard
+ +


+ +

Project Description

+ +

This project involves building a solid theoretical foundation in RL concepts, implementing key algorithms like Dynamic Programming, Monte Carlo Methods, and Policy Gradient Methods, and applying them to different tasks. + By experimenting with advanced techniques such as Double DQN and Actor-Critic methods, you will optimize agent performance and analyze results. + Comprehensive documentation and evaluation will enhance learning and provide insights for future applications, making this project a stepping stone to mastering RL.

+ + +

Pre-requisites

+ +

Basic Python Programming
+Reinforcement Learning Basics
+ + +

Resources

+ +

OpenAI Gym Documentation
+Sutton and Barto- Book on Reinforcement Learning
+ + +

+ +
+ + +
+ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + From 36b27603251cdef8872592a3e7771b6c0ab13bff Mon Sep 17 00:00:00 2001 From: Aditya Vivekanand <142730385+adityavivekanand@users.noreply.github.com> Date: Wed, 12 Jun 2024 16:15:45 +0530 Subject: [PATCH 3/4] Update index.html --- _site/projects/index.html | 14 ++++++++++++++ 1 file changed, 14 insertions(+) diff --git a/_site/projects/index.html b/_site/projects/index.html index 2c02383..9cf4fa2 100644 --- a/_site/projects/index.html +++ b/_site/projects/index.html @@ -249,6 +249,20 @@

convolutions on FPGA

+ + +
+
+ +
+
+

Reinforcement Learning

+

To understand and explore Reinforcement LEarning through OpenAI Gym's environments.

+
+
+
+
+
From 95ea27407ba8bbd19834c3ed5cf46597ad4b4457 Mon Sep 17 00:00:00 2001 From: adityavivekanand Date: Wed, 12 Jun 2024 17:08:22 +0530 Subject: [PATCH 4/4] update changes --- _projects/GymMaster.md | 10 +- _site/projects/GymMaster/index.html | 316 ++++++++++++++++++++++++++++ _site/projects/index.html | 63 +++--- 3 files changed, 355 insertions(+), 34 deletions(-) create mode 100644 _site/projects/GymMaster/index.html diff --git a/_projects/GymMaster.md b/_projects/GymMaster.md index 1b33d83..adee3d0 100644 --- a/_projects/GymMaster.md +++ b/_projects/GymMaster.md @@ -1,7 +1,8 @@ --- -Layout: Page -Title: GymMaster -Description: Project to gain a deep understanding of Reinforcement Learning (RL) by systematically exploring and solving various OpenAI Gym environments. +layout: page +title: GymMaster +description: Project to gain a deep understanding of Reinforcement Learning (RL) by systematically exploring and solving various OpenAI Gym environments. +importance: 1 --- | Project Domains | Mentors | Project Difficulty | @@ -29,8 +30,9 @@ Comprehensive documentation and evaluation will enhance learning and provide ins - [OpenAI Gym Document](https://www.gymlibrary.dev/content/basic_usage/) - [Sutton and Barto](https://www.google.co.in/books/edition/Reinforcement_Learning_second_edition/uWV0DwAAQBAJ?hl=en&gbpv=1&printsec=frontcover) + ### Mentor Aditya Vivekanand - avivekanand_b22@et.vjti.ac.in -> If you have any doubts regarding this project or any difficulty in understanding the pre-requisites videos you reach out to the mentor. +> If you have any doubts regarding this project or any difficulty in understanding the pre-requisites videos you reach out to the mentor. \ No newline at end of file diff --git a/_site/projects/GymMaster/index.html b/_site/projects/GymMaster/index.html new file mode 100644 index 0000000..95c2478 --- /dev/null +++ b/_site/projects/GymMaster/index.html @@ -0,0 +1,316 @@ + + + + + + + + + + + + + GymMaster | Eklavya 2024 + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
+ + + + + + +
+ +
+ +
+ + + +
+ + +
+ +
+

GymMaster

+

Project to gain a deep understanding of Reinforcement Learning (RL) by systematically exploring and solving various OpenAI Gym environments.

+
+ +
+ + + + + + + + + + + + + + + +
Project DomainsMentorsProject Difficulty
Reinforcement learning, OpenAI Gym, TenserFlow/ PyTorch, ML basicsAditya VivekanandMedium to Hard
+ +


+ +

Project Description

+ +

This project involves building a solid theoretical foundation in RL concepts, implementing key algorithms like Dynamic Programming, Monte Carlo Methods and Policy Gradient Methods, and applying them to different tasks. +By experimenting with advanced techniques such as Double DQN and Actor-Critic methods, you will optimize agent performance and analyze results. +Comprehensive documentation and evaluation will enhance learning and provide insights for future applications, making this project a stepping stone to mastering RL.

+ +

Pre-requisites

+ + + +
+

It is recommended that candidates interested in this project go through the above resources. This will give you an advantage over others during interview for this project.

+
+ +

References

+ + + +

Mentor

+ +

Aditya Vivekanand - avivekanand_b22@et.vjti.ac.in

+ +
+

If you have any doubts regarding this project or any difficulty in understanding the pre-requisites videos you reach out to the mentor.

+
+ +
+ +
+ + +
+ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/_site/projects/index.html b/_site/projects/index.html index 9cf4fa2..2d01145 100644 --- a/_site/projects/index.html +++ b/_site/projects/index.html @@ -85,6 +85,9 @@
  • Eklavya Projects(current)
    • +
  • + Tasks +
    • - +
    -

    EMG-Armband

    -

    Design a EMG Armband with Esp-32 and implement ML model on it to detect Hand Movements

    +

    CONVOLUTIONS ON FPGA

    +

    To perform convolution for NxN image and futher applications on image processing on FPGA

    @@ -155,11 +158,11 @@

    EMG-Armband

    - +
    -

    GyroGlider

    -

    Implementing Self Balancing on SRA's latest morphable bot-EvoBorne in a semi-drone mode.

    +

    EMG-Armband

    +

    Design a EMG Armband with Esp-32 and implement ML model on it to detect Hand Movements

    @@ -169,11 +172,11 @@

    GyroGlider

    - +
    -

    Micromouse

    -

    Design a micromouse PCB from scratch and implement maze floodfill algorithms on it!

    +

    GymMaster

    +

    Project to gain a deep understanding of Reinforcement Learning (RL) by systematically exploring and solving various OpenAI Gym environments.

    @@ -183,11 +186,11 @@

    Micromouse

    - +
    -

    Titan-Quadruped

    -

    Making VJTI's first Quadruped from scratch

    +

    GyroGlider

    +

    Implementing Self Balancing on SRA's latest morphable bot-EvoBorne in a semi-drone mode.

    @@ -197,11 +200,11 @@

    Titan-Quadruped

    - +
    -

    Vision Transformers From Scratch

    -

    Implementing a Vision Transformers Model From Scratch

    +

    Micromouse

    +

    Design a micromouse PCB from scratch and implement maze floodfill algorithms on it!

    @@ -211,53 +214,53 @@

    Vision Transformers From Scratch

    - +
    -

    Video Card on FPGA

    -

    Design a video card used in computers on a FPGA

    +

    Titan-Quadruped

    +

    Making VJTI's first Quadruped from scratch

     -
    +
    - +
    -

    VoiceVideo-Manipulator

    -

    The project aims to develop a robotic manipulator system equipped with both video input capabilities and speech recognition for accepting spoken commands.

    +

    Vision Transformers From Scratch

    +

    Implementing a Vision Transformers Model From Scratch
    - +
    - +
    -

    convolutions on FPGA

    -

    To perform convolution for NxN image and futher applications on image processing on FPGA

    +

    Video Card on FPGA

    +

    Design a video card used in computers on a FPGA
    - +
    - +
    -

    Reinforcement Learning

    -

    To understand and explore Reinforcement LEarning through OpenAI Gym's environments.

    +

    VoiceVideo-Manipulator

    +

    The project aims to develop a robotic manipulator system equipped with both video input capabilities and speech recognition for accepting spoken commands. This system will enable users to control the robotic manipulator intuitively through verbal instructions and visual feedback.