ankeshanand

ankeshanand.github.io

Personal webpage

auv-simulator

Simulates the working environment for Kraken-our Autonomous Underwater Vehicle.

benchmark

Update: The repository has been moved to https://github.com/BRL-CAD/benchmark. Subsequent development will take place there.

blindfold-baselines-eqa

Simple question-only baselines for Embodied Question Answering

deep-clickbait-detection

Source code for the paper "We used Neural Networks to Detect Clickbaits: You won't believe what happened Next!"

jaankari

An Android app that makes Information and entermainment accessible to phones in remote areas with low connectivity using Wifi P2P networks.

neural-cryptography-tensorflow

Neural Networks that invent their own encryption :key:

py-gfycat

A Python client for the Gfycat API.

atari-representation-learning

Code for "Unsupervised State Representation Learning in Atari"

spr

Code for "Data-Efficient Reinforcement Learning with Self-Predictive Representations"

ankeshanand/neural-cryptography-tensorflow

Neural Networks that invent their own encryption :key:

ankeshanand/py-gfycat

A Python client for the Gfycat API.

ankeshanand/deep-clickbait-detection

Source code for the paper "We used Neural Networks to Detect Clickbaits: You won't believe what happened Next!"

ankeshanand/blindfold-baselines-eqa

Simple question-only baselines for Embodied Question Answering

ankeshanand/ankeshanand.github.io

Personal webpage

ankeshanand/baselines

OpenAI Baselines: high-quality implementations of reinforcement learning algorithms

ankeshanand/awd-lstm-lm

LSTM and QRNN Language Model Toolkit for PyTorch

ankeshanand/awesome-self-supervised-learning

A curated list of awesome self-supervised methods

ankeshanand/byteNet-tensorflow

ByteNet for character-level language modelling

ankeshanand/coinrun

Code for the paper "Quantifying Transfer in Reinforcement Learning"

ankeshanand/CSrankings

A web app for ranking computer science departments according to their research output in selective venues.

ankeshanand/cybersource-flex-samples

Samples for CyberSource Flex service

ankeshanand/DCGAN-tensorflow

A tensorflow implementation of "Deep Convolutional Generative Adversarial Networks"

ankeshanand/EfficientZero

Open-source codebase for EfficientZero, from "Mastering Atari Games with Limited Data" at NeurIPS 2021.

ankeshanand/Folder-Structure-Conventions

Folder / directory structure options and naming conventions for software projects

ankeshanand/Generative-Latent-Optimization-Tensorflow

Tensorflow implementation of Generative Latent Optimization (GLO) proposed by Facebook AI Research

ankeshanand/lucid

A collection of infrastructure and tools for research in neural network interpretability.

ankeshanand/mujoco-py

MuJoCo is a physics engine for detailed, efficient rigid body simulations with contacts. mujoco-py allows using MuJoCo from Python 3.

ankeshanand/ProMP

ProMP: Proximal Meta-Policy Search

ankeshanand/pytorch

Tensors and Dynamic neural networks in Python with strong GPU acceleration

ankeshanand/pytorch-a2c-ppo-acktr-gail

PyTorch implementation of Advantage Actor Critic (A2C), Proximal Policy Optimization (PPO), Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation (ACKTR) and Generative Adversarial Imitation Learning (GAIL).

ankeshanand/pytorch-maml-rl

Reinforcement Learning with Model-Agnostic Meta-Learning in Pytorch

ankeshanand/Rainbow

Rainbow: Combining Improvements in Deep Reinforcement Learning

ankeshanand/ray

A system for parallel and distributed Python that unifies the ML ecosystem.

ankeshanand/retro-baselines

Publicly releasable baselines for the Retro contest

ankeshanand/retro-contest

OpenAI Retro Contest

ankeshanand/rlpyt

Reinforcement Learning in PyTorch

ankeshanand/spinningup

Spinning Up in Deep RL

ankeshanand/vigilworkshop.github.io

ankeshanand/welcome_tutorials

Various tutorials given for welcoming new students at MILA.