Train and compare PPO, A2C and DQN agents on a custom OpenAI Gym Snake environment (2 M timesteps, Stable-Baselines3)
-
Updated
Mar 10, 2026 - Python
Train and compare PPO, A2C and DQN agents on a custom OpenAI Gym Snake environment (2 M timesteps, Stable-Baselines3)
Reinforcment learning algorithms
A university project where we implement and experiment with different Reinforcement Learning algorithms and trying to optimize the CartPole environment from OpenAI Gym.
Kung Fu Master A2C Agent is a PyTorch implementation of the Advantage Actor–Critic (A2C) algorithm, engineered to learn and play the Atari classic Kung Fu Master. It uses Gymnasium (with ALE ROMs) to manage multiple parallel environments and a custom preprocessing wrapper.
resource aware PCG for game level generation with human feedback, Meta Learning, a Dashboard and Solvability guardrail
Deep reinforcement learning experiments
A personal journey through reinforcement learning, inspired by Sutton & Barto’s classic book. This repository contains my step-by-step coding projects, experiments, and notes as I learn and implement key RL concepts — from multi-armed bandits to advanced policy gradient methods.
Train and evaluate deep reinforcement learning agents (DQN, PPO, A2C) to play the classic Snake game using Stable-Baselines3 and PyTorch.
Deep Reinforcement Learning: On-Policy Actor Critic methods. An implementation of Advantage Actor-Critic (A2C) and Proximal Policy Optimization (PPO) on the PyTorch Lightning framework.
2024 Spring, Principles of Reinforcement Learning
A collection of AIs made with PyTorch
Implementation of Proximal Policy Optimization (PPO) based on the original PPO paper for continuous control tasks in MuJoCo environments.
Implementations from the free course Deep Reinforcement Learning with Tensorflow and PyTorch
Third homework for the Reinforcement Learning course
Some RL algorithm implementation (PyTorch) (Colab executable)
Policy iteration, REINFORCE, A2C, and A3C for decision-making, LunarLander control, and vision-based robotic grasping in PyBullet.
PyTorch implementation of Asynchronous (and Synchronous) Advantage Actor Critic
RL learning model for Hola's Haggling Challenge
To associate your repository with the a2c topic, visit your repo's landing page and select "manage topics."