Pinned Repositories
aafu
Portfolio theme with blog
COMP-767-Reinforcement-Learniing
Contains the assignment for COMP-767-Reinforcement Learning Winter 2019
ENF-Extraction-of-Bangladesh-Grid
Process of collecting Power Recording from Bangladesh Grid is described. More than 10 Hours of data has published here. We also extracted ENF from recorded power file and compared with online available grid data all around the world.
off_policy_ac
Contains PyTorch Implementation of the following off policy actor critic algorithms
Off_Policy_Adversarial_Inverse_Reinforcement_Learning
Implementation of Off Policy Adversarial Inverse Reinforcement Learning
Offline-Reinforcement-Learning-Algorithms
PyTorch Implementation of Offline Reinforcement Learning algorithms
pentago_twist
PyTorch-implementation-DICE-algorithms
PyTorch-implementation-DICE-algorithms
Simplest-and-Most-Affordable-GPS-Tracking-System
Sole idea of this project was to make cheapest GPS tracking system possible. Proposed GPS tracker was made for initially a Lab Project. We didn’t want to spend money on buying GPS module which would cost around 100 USD in Bangladesh and smart coding to execute it properly. So we decided to make the simplest and most affordable GPS tracker possible. We wanted to use our smart cell phone which already has an imbedded GPS and use MATLAB code to build a system that itself provided update GPS location once initialized.
Sp-Cup-2016
The Electric Network Frequency (ENF) is the supply frequency of power distribution networks, which can be captured by multimedia signals recorded near electrical activities. It normally fluctuates slightly over time from its nominal value of 50 Hz/60 Hz. The ENF remain consistent across the entire power grid. This has led to the emergence of multiple forensic application like estimating the recording location and validating the time of recording. Recently an ENF based Machine Learning system was proposed which infers the region of recording from the power grids ENF signal extracted from the recorded multimedia signal, with the help of relevant features. In this work, we report some features novel to this application which serve as identifying characteristics for detecting the region of origin of the multimedia recording. In addition to the ENF variation itself, the utilization of the ENF harmonics pattern extracted from the media signals as novel features enables a more accurate identification of the region of origin. These characteristics were used in a multiclass machine learning implementation to identify the grid of the recorded signal.
SaminYeasar's Repositories
SaminYeasar/Off_Policy_Adversarial_Inverse_Reinforcement_Learning
Implementation of Off Policy Adversarial Inverse Reinforcement Learning
SaminYeasar/pentago_twist
SaminYeasar/Offline-Reinforcement-Learning-Algorithms
PyTorch Implementation of Offline Reinforcement Learning algorithms
SaminYeasar/ENF-Extraction-of-Bangladesh-Grid
Process of collecting Power Recording from Bangladesh Grid is described. More than 10 Hours of data has published here. We also extracted ENF from recorded power file and compared with online available grid data all around the world.
SaminYeasar/off_policy_ac
Contains PyTorch Implementation of the following off policy actor critic algorithms
SaminYeasar/PyTorch-implementation-DICE-algorithms
PyTorch-implementation-DICE-algorithms
SaminYeasar/auto-drac
Automatic Data-Regularized Actor-Critic (Auto-DrAC)
SaminYeasar/awr
Implementation of advantage-weighted regression.
SaminYeasar/CQL
Conservative Q Learning on top of SAC
SaminYeasar/d4rl-atari
Datasets for data-driven deep reinforcement learning with Atari (wrapper for datasets released by Google)
SaminYeasar/DAPD
Official Implementation of Data Adaptive Pathway Discovery (DAPD) for Online RL
SaminYeasar/decision-transformer
Official codebase for Decision Transformer: Reinforcement Learning via Sequence Modeling.
SaminYeasar/Deep-Learning-Algos
Problems are solved using Tensorflow, Deep Learning, Machine Learning
SaminYeasar/DeepMimic_mujoco
DeepMimic Mujoco version; Python only; No Bullet, No C++
SaminYeasar/diffuser
Code for the paper "Planning with Diffusion for Flexible Behavior Synthesis"
SaminYeasar/DrM
DrM, a visual RL algorithm, minimizes the dormant ratio to guide exploration-exploitation trade-offs, achieving significant improvements in sample efficiency and asymptotic performance across diverse domains.
SaminYeasar/drqv2
DrQ-v2: Improved Data-Augmented Reinforcement Learning
SaminYeasar/google-research
Google Research
SaminYeasar/gym-minigrid
Minimalistic gridworld package for OpenAI Gym
SaminYeasar/imitation_learning
PyTorch implementation of some reinforcement learning algorithms: Advantage Actor Critic (A2C), Proximal Policy Optimization (PPO), V-MPO, Behavior Cloning (BC). More algorithms will be added.
SaminYeasar/metaworld
An open source robotics benchmark for meta- and multi-task reinforcement learning
SaminYeasar/offline-rl-minigrid
SaminYeasar/oop-python
Object-Oriented Programming in Python
SaminYeasar/rad_procgen
RAD: Reinforcement Learning with Augmented Data (code for procgen experiments)
SaminYeasar/redo
ReDo: The Dormant Neuron Phenomenon in Deep Reinforcement Learning (pytorch)
SaminYeasar/saminyeasar.github.io
Source code for http://www.jesshamrick.com/
SaminYeasar/saminyeasar___.github.io
SaminYeasar/sqil-atari
Implementation of SQIL for Atari games
SaminYeasar/the-incredible-pytorch
The Incredible PyTorch: a curated list of tutorials, papers, projects, communities and more relating to PyTorch.
SaminYeasar/vector-quantize-pytorch
Vector Quantization, in Pytorch