Pinned Repositories
503GradProject
656F23_Project
AlphaReader
An android application for viewing HTML pages (books) and syncing in multiple devices.
Hybrid_Local_Planner
This is an implementation of ROS Local Planner using the Dijkstra's algorithm and the Hybrid A star algorithm
PCTemplate
Programming Contest templates, used by UIU_Fractals
ProjectNavigation
Udacity DRL ND, Project Navigation. In this project, I used Deep Q-Learning (with Dueling Network Architectures, Double Q-learning, and Prioritized Experience Replay) for solving the Unity Banana environment.
ProjectTennis
In this project, I solved the Unity Tennis environment using MADDPG algorithm.
RL
My experiments with different Reinforcement Learning algorithms and environments.
TGR
Raspberry Pi (4B) based 4wd robot, created for real world ML/RL based projects.
relod
An efficient remote-onboard architecture for real-time Reinforcement Learning
fahimfss's Repositories
fahimfss/Hybrid_Local_Planner
This is an implementation of ROS Local Planner using the Dijkstra's algorithm and the Hybrid A star algorithm
fahimfss/TGR
Raspberry Pi (4B) based 4wd robot, created for real world ML/RL based projects.
fahimfss/ProjectTennis
In this project, I solved the Unity Tennis environment using MADDPG algorithm.
fahimfss/ProjectNavigation
Udacity DRL ND, Project Navigation. In this project, I used Deep Q-Learning (with Dueling Network Architectures, Double Q-learning, and Prioritized Experience Replay) for solving the Unity Banana environment.
fahimfss/RL
My experiments with different Reinforcement Learning algorithms and environments.
fahimfss/PCTemplate
Programming Contest templates, used by UIU_Fractals
fahimfss/503GradProject
fahimfss/656F23_Project
fahimfss/AlphaReader
An android application for viewing HTML pages (books) and syncing in multiple devices.
fahimfss/DuckieRepo503
A repository for the CMPUT 503 (Experimental Mobile Robotics) course
fahimfss/EGAGP
Undergraduate research paper implementation.
fahimfss/fahimfss.github.io
fahimfss/GREMate
fahimfss/jaxrl
JAX (Flax) implementation of algorithms for Deep Reinforcement Learning with continuous action spaces.
fahimfss/mujoco_tests
fahimfss/PodcastSA
App for listening to scientificamerican.com podcasts in android
fahimfss/ProjectReacher
In this project, I used the Actor-Critic algorithm (A2C GAE) for solving the Unity Reacher environment.
fahimfss/Projects
My undergraduate projects
fahimfss/rl655_franka
fahimfss/upgd
a continual learning optimizer mitigating catastrophic forgetting and loss of plasticity