Pinned Repositories
ActiveInference_PolicyLearning
Scripts used for the Active Inference Policy Learning paper
Analysis_CoBrA
Some analysis scripts to use around the lab.
Ants_Pomodoro
Pomodoro Timer for Study-Rest Cycle
ClinVar_PathoID
Searches up a list of variants to identify clinical significance and (if present) condition(s).
COMP551_Applied_ML
Some algorithms and course works from COMP551: Applied Machine Learning
Connect4-Bot
A bot that plays Connect 4
credit-transport
MSc Research
ElectrophysRL
RL agent and activation recordings
gym_RL
Playing around with control and reinforcement learning using the Open AI Gym
sr-return
MSc Research
im-ant's Repositories
im-ant/ActiveInference_PolicyLearning
Scripts used for the Active Inference Policy Learning paper
im-ant/Analysis_CoBrA
Some analysis scripts to use around the lab.
im-ant/COMP551_Applied_ML
Some algorithms and course works from COMP551: Applied Machine Learning
im-ant/Connect4-Bot
A bot that plays Connect 4
im-ant/credit-transport
MSc Research
im-ant/ElectrophysRL
RL agent and activation recordings
im-ant/gym_RL
Playing around with control and reinforcement learning using the Open AI Gym
im-ant/sr-return
MSc Research
im-ant/BARL2020-Successor-Return-Error
Lambda Successor Return Error for NeurIPS 2020 Biological and Artificial RL Workshop
im-ant/Capsules-Guys
COMP551 Fall 2018, Final Project
im-ant/COMP767-PGM
Code relating to COMP767 - Probabilistic Graphical Models class
im-ant/dreamerv3-torch
Implementation of Dreamer v3 in pytorch.
im-ant/e3b
Official repo for the E3B algorithm described in the paper "Exploration via Elliptical Episodic Bonuses".
im-ant/Genomics_Preprocessing
Script for general pre-processing of genomics datasets
im-ant/gradient_dim
Gradient dimensionality for optimization
im-ant/IFT6135-rep-learning
Coursework for IFT6135: Representation Learning at UdeM. Winter 2020.
im-ant/im-ant.github.io
im-ant/InstaGraph
im-ant/latent-td-error
Inferring TD learning parameters from errors
im-ant/McGill-Web-Access
Tools used to programatically access McGill websites
im-ant/NEURM012_classProject
im-ant/overparameterized-optim
Playing with overparameterized optimization
im-ant/ProductivityLog
Things to help analyze workflow and productive hours
im-ant/return-mixture
im-ant/RL-767
Coursework and projects relating to COMP767: RL
im-ant/rlpyt
Reinforcement Learning in PyTorch
im-ant/sample-factory-ppo
High throughput synchronous and asynchronous reinforcement learning
im-ant/saving-sample-factory
High throughput synchronous and asynchronous reinforcement learning
im-ant/sparse-external-memory
Ideas surrounding external memory and sparse attention
im-ant/url_benchmark