koulanurag
PostDoc @ Microsoft Research | Ph.D. - Oregon State University | Deep Reinforcement Learning
Microsoft New York, New York
Pinned Repositories
conformal
Conformal prediction is a framework for providing accuracy guarantees on the predictions of a base predictor
dream-and-search
Code for "Dream and Search to Control: Latent Space Planning for Continuous Control"
gym-cartpole-continuous
CartPole env. with continuous action space
gym_x
Gym environments for capture properties of hidden states(hx) of recurrent networks.
ma-gym
A collection of multi agent environments based on OpenAI gym.
minimal-marl
Minimal implementation of multi-agent reinforcement learning algorithms
mmn
Moore Machine Networks (MMN): Learning Finite-State Representations of Recurrent Policy Networks
muzero-pytorch
Pytorch Implementation of MuZero
variable-td3
Learning n-step actions for control tasks
visTorch
Interacting with Latent Space of AutoEncoder
koulanurag's Repositories
koulanurag/ma-gym
A collection of multi agent environments based on OpenAI gym.
koulanurag/muzero-pytorch
Pytorch Implementation of MuZero
koulanurag/mmn
Moore Machine Networks (MMN): Learning Finite-State Representations of Recurrent Policy Networks
koulanurag/minimal-marl
Minimal implementation of multi-agent reinforcement learning algorithms
koulanurag/visTorch
Interacting with Latent Space of AutoEncoder
koulanurag/conformal
Conformal prediction is a framework for providing accuracy guarantees on the predictions of a base predictor
koulanurag/dream-and-search
Code for "Dream and Search to Control: Latent Space Planning for Continuous Control"
koulanurag/gym-cartpole-continuous
CartPole env. with continuous action space
koulanurag/gym_x
Gym environments for capture properties of hidden states(hx) of recurrent networks.
koulanurag/marl-pytorch
Pytorch Implementations of Multi Agent Reinforcement Learning(marl) algorithms
koulanurag/deep-conformal
Applying Conformal Prediction over Deep Neural Nets
koulanurag/opcc
Benchmark for "Offline Policy Comparison with Confidence"
koulanurag/policybazaar
A collection of multi-quality policies for continuous control tasks.
koulanurag/variable-td3
Learning n-step actions for control tasks
koulanurag/maze-world
Random maze environments with different size and complexity for reinforcement learning research.
koulanurag/opcc-baselines
Baselines for "Offline Policy Comparison with Confidence"
koulanurag/pfa
Policy Fusion Architecture (PFA): We investigate policy gradient approaches for reward decomposition in reinforcement Learning
koulanurag/tensorboard2seaborn
Plot Tensorflow Summary Event in a Beautiful Way 🌈
koulanurag/vpn
PyTorch implementation of Value Prediction Network (VPN) :construction: :construction_worker:
koulanurag/pid-pendulum
PID controller for open-ai gym's Pendulum.
koulanurag/abp
A library to create adaptive programs (abp) via Reinforcement Learning
koulanurag/bmi
BMI Dashboard using NodeJs
koulanurag/card-arrangement-game
Card Arrangement Game to introduce statistical notions in fun way :game_die: :black_joker: :slot_machine:
koulanurag/chatter-nodejs
Trying to make a chat channel similar to IRC. (Inspired by usage of slack)
koulanurag/d4rl
A benchmark for offline reinforcement learning.
koulanurag/data-science-coursera
Tracking progress in data science course on Coursera
koulanurag/device-config-app
Primary purpose of app is to configure Echo Sounders.
koulanurag/gym-sokoban
Sokoban environment for OpenAI Gym
koulanurag/sweatram_mean
SweatRam's Dashboard using a Mean Stack
koulanurag/tweet-node
This project is to analyse real time tweets