Name: Abhinav Bhatia
Type: User
Company: University of Massachusetts, Amherst
Bio: PhD Student @UMass Amherst
AI, Sequential Decision Making, Deep
Reinforcement Learning
Location: Amherst, MA, USA
Blog: https://abhinavbhatia.me
Abhinav Bhatia's Projects
Julia Implementation of Anytime Weighted A* (AWA*) and Randomized Weighted A* (RWA*) algorithm
OpenAI Baselines: high-quality implementations of reinforcement learning algorithms
Abhinav Bhatia's Personal Webpage
Compiler construction project for college course. My team topped the practicals :)
Bike Sharing System gym (openai) RL environment
Emergency Response System (ERS) (Ambualance allocation problem) simualtor gym environment.
Unity game engine like framework to build OPENAI gym environments.
Curated decibans of Julia programming language.
Decision-theoretic metareasoning to control hyperparameter and stopping point of anytime algorithms using deep reinforcement learning.
A model-free metareasoning library for interrupting and adjusting the parameters of anytime algorithms.
A reinforcement learning package for Julia
This repo is not maintained anymore. Some algorithms for solving deep RL problems. Using TensorFlow.
Version 3.0.0 Pytorch implementations of DQN, DDQN, DDPG, SAC, Discrete SAC. With more features :)
A Reinforcement Learning Julia package that provides a framework and tools for developing new RL environments and RL algorithms.
Source code for paper: RL^3: Boosting Meta Reinforcement Learning via RL inside RL^2.
Julia implementation of RRT* motion planning algorithm.
A tennis game environment implemented in Java for RL purposes.