pbarde Goto Github PK

alfred

Just some boilerplate code for machine learning projects

artificialbeecolony

Modified version of https://rwuilbercq.github.io/Hive/ one to visualize Rastrigin solution and solve TSP

asaf-playground

Pommerman's playground adapted for ASAF paper

bandit

Implementation of "Best-arm identification algorithms for multi-armed bandits in the fixedconfidence setting, Kevin Jamieson and Robert Nowak, CISS, 2014"

coordination-marl

Code to reproduce experiments from:

diff_abms_tutorial

"Differentiable Agent-Based Models" tutorial presented at AAMAS 2024.

dp

Value iteration, Policy iteration and Modified Policy iteration on simple gridworld

dqn_flappy_bird

A DQN from raw pixels input that solves the Flappy Bird game

flow-zsc

Computational framework for reinforcement learning in traffic control

hopfielnetwork

Modeling the Stroop Effect using Hopfield Networks

iboat-pmcts

A Parallel Monte-Carlo Tree Search using multiprocessing and real weather forecasts to address long-term optimal path planning under uncertainty for autonomous sailboat

iboat-project

Academic Project on optimal trajectory planning for autonomous sailboats using Markov decision process

iboat_rl

Reinforcement learning tools and boat simulator to avoid stall

ift6135h19_assignment

imageclassif

MLP, CNN and CIFARResNet18 applied to image classification

naturallanguageprocessing

RNN, GRU, Transformer

papernotes

Some reading notes and screen shots of Machine Learning papers

pbarde.github.io

Paul Barde - Personal Website - https://pbarde.github.io/

rlchallenge

RL class' challenge files

tabularrl

Sarsa, Expected Sarsa and Q-learning

ubisoft-laforge-asaf

Asaf

understanding-and-visualizing-cnn

Jupyter notebook that uses keras-vis library to visualize Activation, Salience and Grad-Cam on VGG16 convNet