RL agent that is trained to catch moving pucks in a complex environment, with DQN, AC, A2C and more.

PyTorch implementation of Asynchronous (and Synchronous) Advantage Actor Critic

Example A2C implementation with ReLAx

The pytorch implemetation of a2c

First Place Reinforcement Learning solution code and a writeup for the AI RoboSoccer Competition.

This repository contains the implementation of the K-workers, n-step Advantage Actor-Critic (A2C) algorithm applied to the CartPole environment, as part of a reinforcement learning project for the EPFL Spring Semester 2024 course on Artificial Neural Networks and Reinforcement Learning.

Multi-task learning with Advantage Actor Critic and sharing experience

This repository contains my assignment solutions for the Deep Learning course (M2177.003100_002) offered by Seoul National University (Fall 2019).

Training a Reinforcement Learning Agent to Play Flappy Bird.

This repository contains the implementation of the K-workers, n-step Advantage Actor-Critic (A2C) algorithm applied to the CartPole environment, as part of a reinforcement learning project for the EPFL Spring Semester 2024 course on Artificial Neural Networks and Reinforcement Learning.

Implementations of deep reinforcement learning algorithms.

Solving CartPole-v1 environment in Keras with Advantage Actor Critic (A2C) algorithm an Deep Reinforcement Learning algorithm

Code for Hands On Intelligent Agents with OpenAI Gym book to get started and learn to build deep reinforcement learning agents using PyTorch

It's a Raspberry Pi Pokémon that gamifies WiFi Hacking by learning from its surrounding WiFi environment utilising deep Reinforcement Learning.

Deep reinforcement learning package for torch7

Official implementation of the AAAI 2021 paper Deep Bayesian Quadrature Policy Optimization.

The friendly robot that beats you in Yahtzee 🤖 🎲

MLP-framework (pure numpy) and DDQN-framework for OpenAI's Gym games. +test code for PPO added. +Hindsight Experience Replay(HER) bitflip-DQN example. +prioritized replay.