sumitsk

marl_transfer

Code for paper 'Learning transferable cooperative behaviors in multi-agent teams' (ICML 2019)

HER

PyTorch Implementation of Hindsight Experience Replay

MOSM-AL

Active Learning of the distribution of multiple correlated target features with Multiple Output Spectral Mixture Kernels Gaussian Processes

algp

Code for Active Learning with Gaussian Processes for High Throughput Phenotyping paper (https://arxiv.org/abs/1901.06803) (AAMAS 2019).

cspace_belief

Code for the paper Learning Configuration Space Belief Model from Collision Checks for Motion Planning (https://arxiv.org/abs/1901.07646)

crnp

Conditional recurrent neural processes

DDPG

DQN

Pytorch Implementation of DQN and Dueling DQN models.

GANs

Implementation of GAN algorithms

MOGP-AL

GPyTorch Implementation of Near-Optimal Active Learning of Multi-Output Gaussian Processes

gpytorch

A highly efficient and modular implementation of Gaussian Processes in PyTorch

gym_vecenv

Python3 wrapper for running multiple OpenAI Gym environments in parallel

LAL

This project contains code for paper Ksenia Konyushkova, Raphael Sznitman, Pascal Fua 'Learning Active Learning from Data', NIPS 2017

leetcode

Leetcode Programming questions solutions

multiagent-particle-envs

oyster

In-progress implementation of Efficient Off-policy Meta-learning via Probabilistic Context Variables (PEARL)

pytorch-pg-rllab

rllab

rllab is a framework for developing and evaluating reinforcement learning algorithms, fully compatible with OpenAI Gym.

sac

Soft Actor-Critic

sumitsk.github.io

My homepage at https://sumitsk.github.io.

sumitsk_old_homepage

Homepage