hatebunnyplzzz Goto Github PK

cartpole-double-ql

Solving the OpenAI gym's CartPole environment using the Double Q Learning approach.

cartpole-sarsa

In this repository, we'll be looking at the code presenting the algorithm named SARSA by solving the CartPole-v1 environment of OpenAI Gym

ctgan

Conditional GAN for generating synthetic tabular data.

custom-gridworld-rl-environments

Custom GridWorld environment problem solving using Q-Learning Epsilon-greedy approach.

d3rlpy

An offline deep reinforcement learning library

deeprl

PyTorch implementations of several state-of-the-art Deep Reinforcement Learning Algorithms

drumkit

gan-for-tabular-data

We well know GANs for success in the realistic image generation. However, they can be applied in tabular data generation. We will review and examine some recent papers about tabular GANs in action.

intro-to-policy-search

Introduction to policy search

lightsaber-vcss

Lightsaber animation with diff colors using vanilla CSS

mlaiblogs

moder-card

A simple Card/tile smooth animation using vanilla css

monte-carlo-control

In this post, I'll be solving the game of BlackJack from OpenAI's Gymnasium using the approach of Monte Carlo Control

multi-arm-bandit

Solution to basic multi-arm bandit problem using action-value functions and epsilon-greedy approach

off-policy-mcc

Successor of the previous post about the Monte Carlo Control by playing the game of BlackJack from the ToyText environments from the OpenAI Gym. In this post we will be changing our approach to a Off-Policy MC Control

pbdl-book

Welcome to the Physics-based Deep Learning Book (v0.2)

policy-evaluation

Hardcoding the policy evaluation approach to our custom hardcoded RL GirdWorld game environment

policy-search-explained

How a RL agent performs while interacting with the environment via the notion of policy instead of a value function

ray

Ray is a unified framework for scaling AI and Python applications. Ray consists of a core distributed runtime and a toolkit of libraries (Ray AIR) for accelerating ML workloads.

socionet

story

tindog

torch-ngp

A pytorch CUDA extension implementation of instant-ngp (sdf and nerf), with a GUI.

transformers

A brief introduction to transformer network

typewriter

Typewriter effect achieved using Vanilla CS

webdev1cv