adi3e08

adi3e08.github.io

Github Pages template for academic personal websites, forked from mmistakes/minimal-mistakes

Physics_Informed_Model_Based_RL

We learn the dynamics model of a robot using a physics-informed neural network and use it to train a model-based RL algorithm.

adi3e08

Config files for my GitHub profile.

CS7150-Project-Soft-Actor-Critic

Final project for CS7150 course.

SAC

A clean and minimal implementation of SAC (Soft Actor Critic) algorithm in Pytorch, for continuous action spaces.

PPO

A clean and minimal implementation of PPO (Proximal Policy Optimization) algorithm in Pytorch, for continuous action spaces.

DDPG

A clean and minimal implementation of DDPG (Deep Deterministic Policy Gradient) algorithm in Pytorch.

DQN

A clean and minimal implementation of DQN (Deep Q Learning) algorithm in Pytorch.

A3C

A clean and minimal implementation of A3C (Asynchronous Advantage Actor Critic) algorithm in Pytorch.

tabular_RL

supervised_learning_examples