ehrenbrav / FCEUX_Learning_Environment
A fork of the FCEUX Nintendo emulator to allow it to be used by the Google Deep Q-Network and other machine learning tools.
☆43Updated 8 years ago
Alternatives and similar repositories for FCEUX_Learning_Environment:
Users that are interested in FCEUX_Learning_Environment are comparing it to the libraries listed below
- A modification of Google's Deep Q-Network to learn to play Super Mario Bros.☆168Updated 8 years ago
- ViZDoom Python wrapper☆74Updated last year
- A Tensorflow based implementation of "Asynchronous Methods for Deep Reinforcement Learning": https://arxiv.org/abs/1602.01783☆67Updated 8 years ago
- Add-on for OpenAI Gym that supports automatic downloading of user environments.☆45Updated 7 years ago
- Gym - Doom environments based on VizDoom.☆103Updated 8 years ago
- Benchmarking Canonical Evolution Strategies for Playing Atari☆83Updated 7 years ago
- A parallel version of Trust Region Policy Optimization☆65Updated 8 years ago
- A Python Interface for the Arcade Learning Environment (Shared Object)☆126Updated 4 years ago
- Deepmind's Deep Q Learning on Atari☆45Updated 10 years ago
- tensorflow deep RL hacking on minecraft with malmo☆54Updated 8 years ago
- This is the 0.4 release of the Arcade Learning Environment (ALE), a platform designed for AI research. ALE is based on Stella, an Atari 2…☆160Updated 7 years ago
- ☆117Updated 4 years ago
- Codes of our team for the OpenAI Retro Contest of reinforcement learning☆99Updated 6 years ago
- ☆68Updated 8 years ago
- A method to train DRL model with Tensorflow and Bizhawk.☆23Updated 5 years ago
- Task and example code for the Malmo Collaborative AI Challenge☆154Updated 2 years ago
- Using Asynchronous Deep Reinforcement Learning to play Flappy Bird from pixel input.☆30Updated 7 years ago
- Reproducing MuJoCo benchmarks in a modern, commercial game /physics engine (Unity + PhysX).☆50Updated 3 months ago
- Use Asynchronous advantage actor-critic algorithm (A3C) to play Flappy Bird using Keras☆39Updated 7 years ago
- The original implementation of HyperNEAT in C++☆28Updated 8 years ago
- OpenAI Retro Contest☆65Updated last year
- An implementation of Deep Q-Network using Caffe☆70Updated 9 years ago
- This package allows to use PLE as a gym environment.☆72Updated 4 years ago
- Persistent advantage learning dueling double DQN for the Arcade Learning Environment☆263Updated 7 years ago
- Openai Gym with Dart support☆141Updated 4 years ago
- Deep Attention Recurrent Q-Network☆115Updated 9 years ago
- Implementation of "Action-Conditional Video Prediction using Deep Networks in Atari Games"☆114Updated 9 years ago
- Reinforcement learning models in ViZDoom environment☆132Updated 3 years ago
- Implementation of "Control of Memory, Active Perception, and Action in Minecraft"☆86Updated 8 years ago
- Implimentation of the Model Free Episodic Control paper by Deep Mind : http://arxiv.org/abs/1606.04460☆55Updated 8 years ago