[Official] Exploring Temporal Coherence for More General Video Face Forgery Detection(ICCV 2021)

[CVPR 2023 Highlight] Official implementation of the paper: "AltFreezing for More General Video Face Forgery Detection"

Python geohash library

Code for "Contention Window Optimization in IEEE 802.11ax Networks with Deep Reinforcement Learning" article published at WCNC 2021.

ns3-gym - The Playground for Reinforcement Learning in Networking Research

DeepCC: A Deep Reinforcement Learning Plug-in to Boost the performance of your TCP scheme in Cellular Networks!

Deep Compressive Offloading: Speeding Up Neural Network Inference by Trading Edge Computation for Network Latency

Public facing notes page

Source codes for the book "Reinforcement Learning: Theory and Python Implementation"

Toy case for learning through Reinforcement Learning algorithms how to establish TCP connections.

Deep Reinforcement Learning for Online Computation Offloading in Wireless Powered Mobile-Edge Computing Networks

Using Q-Learning to solve a modified bin packing type problem.

Berkeley CS285 2019 homework solution

Implementation of the Self Paced Reinforcement Learning Experiments

Random-Access Accelerator (RAA): A Framework to speed up the Random-Access procedure in 5G New Radio by enabling D2D communications with BLE

The code for paper titled "Dependency-Aware-Computation-Offloading-for-Mobile-Edge-Computing-with-Edge-Cloud-Cooperation"

Reinforcement Learning based TCP congestion control

Optimization of Offloading Scheme Algorithm for Large Number of Tasks in Mobile-Edge Computing

Device-to-Device (D2D) communication OpenAI Gym environment

Simulated the scenario between edge servers and users with a clear graphic interface. Also, implemented the continuous control with Deep Deterministic Policy Gradient (DDPG) to determine the resour…

Environments and Wrappers for CARLA, designed for ease of use with RL Tasks.

Implementation code of Scan-RL from the 2020 ECCV Workshop paper "Next-Best View Policy for 3D Reconstruction".

The most optimum route from source to target involving the least number of active users using the Minimum Active Node Algorithm (MAN) to reduce the interference and power consumed.