armahmood

totd-rndmdp-experiments

Random MDP experiments on true online TD from a forthcoming work by van Seijen et al. (2015)

nonstationary-experiments

A bunch of stationary and nonstationary experiments comparing LMS, RLS, IDBD and Autostep.

Create-Serial-Port-Packet-Processor

wislstd-experiments

Random walk experiments on WIS-LSTD by Mahmood, van Hasselt, Sutton (2014, nips)

deep-rl

Collection of Deep Reinforcement Learning algorithms

DetectAndTrack

The implementation of an algorithm presented in the CVPR18 paper: "Detect-and-Track: Efficient Pose Estimation in Videos"

gym

A toolkit for developing and comparing reinforcement learning algorithms.

notebooks-1

An attempt to formalize my thoughts. A pythonic approach to mental housekeeping

pytorch

Tensors and Dynamic neural networks in Python with strong GPU acceleration

rnnlm

Tomas Mikolov's Recurrent Neural Networks Language Modeling Toolkit from http://www.rnnlm.org, with tagged historical releases.

scipy

Scipy library main repository

usage-td-experiments

Random MDP experiments on the usage-based step-size adaptation idea by Mahmood and Sutton (2015)

wis-td-experiments

Random MDP experiments on the WIS-based off-policy algorithms by Mahmood and Sutton (2015)

653f20assignment2

Assignment 2, CMPUT 653, Fall 2020

deepdream

repn-learning

Taapas and Rupam's work during Summer 2020

SenseAct

SenseAct: A computational framework for real-world robot learning tasks