Name: SOURADIP CHAKRABORTY
Type: User
Company: University of Maryland
Bio: Ph.D. student, University of Maryland
Past: ML Research@Walmart Labs
Uncertainty and Robustness in Deep Reinforcement Learning
Twitter: SOURADIPCHAKR18
Location: Maryland, USA
Blog: https://souradip-chakraborty.github.io/
SOURADIP CHAKRABORTY's Projects
reinforcement learning with pytorch geometric library
Google Research
The source code for NeurIPS 2020 paper "Graph Policy Network for Transferable Active Learning on Graphs"
Implementation of the paper https://arxiv.org/abs/1603.00448.
Toy problems for OpenAI Gym
Unofficial Pytorch code for "Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models"
HARCNN: End-to-end Deep Learning-based Personalized Human Activity Recognition Framework
Robot Learning from Expert Demonstration Using IRL
Maximum Entropy and Maximum Causal Entropy Inverse Reinforcement Learning Implementation in Python
Build a Jekyll blog in minutes, without touching the command line.
Online and informative thinning of MCMC samples using the Kernelized Stein Discrepancy (KSD)
Posterior Coreset Construction with Kernelized Stein Discrepancy for Model-Based Reinforcement Learning
Code for Reinforcement Learning with Sparse Rewards using Guidance from Offline Demonstration, ICLR 2022 (Spotlight)
This code accompanies the paper "Scalable Multi-Agent Model-Based Reinforcement Learning".
PyTorch Implementation of Momentum-Based Policy Gradient Methods
A pytorch reprelication of the model-based reinforcement learning algorithm MBPO
Code for paper: Model-based Reinforcement Learning for Continuous Control with Posterior Sampling (https://arxiv.org/abs/2012.09613)
Experiment code for "Continuous-Time Model-Based Reinforcement Learning"
Respository for the paper "Optimistic Posterior Sampling for Reinforcement Learning with Few Samples and Tight Guarantees"
PyTorch implementation of the Option-Critic framework, Harb et al. 2016
Policy Gradient algorithms (REINFORCE, NPG, TRPO, PPO)
Basics about Generative modelling and Variational Inference
propaganda detection in news articles
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).
PyTorch implementation of Deep Reinforcement Learning: Policy Gradient methods (TRPO, PPO, A2C) and Generative Adversarial Imitation Learning (GAIL). Fast Fisher vector product TRPO.