vizdoom

Doom-based AI Research Platform for Reinforcement Learning from Raw Visual Information.

C++-based high-performance parallel environment execution engine for general RL environments.

Reinforcement Learning in Keras on VizDoom

Reinforcement learning models in ViZDoom environment

C51-DDQN in Keras

Direct Future Prediction (DFP ) in Keras

DQN, DDDQN, A3C, PPO, Curiosity applied to the game DOOM

Keras implementation of DQN on ViZDoom environment

OpenAI Gym wrapper for ViZDoom enviroments

Continual Reinforcement Learning in 3D Non-stationary Environments

Reinforcement learning in 3D.

Experiment code for testing effect of various action space transformations in reinforcement learning

Implementations of Deep Reinforcement Learning Algorithms and Bench-marking with PyTorch

Gym wrapper for Vizdoom environments

Reinforcement Learning Tutorials & other bedtime stories in PyTorch

😈 Train ViZDoom agents by Reinforcement Learning 👻

PyOblige is Python wrapper for OBLIGE - random level generator for Doom

A2C, ACKTR and A2T implementations for ViZDoom

Test IntelAct vizdoom model

Some Python scripts to test out the Mxnet gluon package for deep learning with Doom

Online exploration of memory reduction strategies of a DRL agent trained to solve a navigation task on ViZDoom

Implementation of the DQN and DRQN algorithms in Keras and tensorflow

This research project investigated Bio-Inspired Neural Network capabilities and State-of-the-Art implementations. As an experiment, it uses ViZDoom; a Doom-based AI Research Platform for Reinforcement Learning from Raw Visual Information.

😺 Imitation Learning based on A3C algorithm 🛠

😅 Progressive Neural Network, based on A3C to train agents on ViZDoom scenarios

submission to TTI-Chicago programming requirement

05-06 Ekim tarihlerinde gerçekleşen DeepCon konferansındaki Derin Pekiştirmeli Öğrenme Atölyesi

A Deep Recurrent Q-Network designed for the 2018 Los Altos Hackathon

Solving games with reinforcement learning