HamidMoghaddam / dota2dqn
This is a deep Q-network (reinforcement learning) AI for Dota 2
☆58Updated 7 years ago
Related projects: ⓘ
- Codes of our team for the OpenAI Retro Contest of reinforcement learning☆100Updated 6 years ago
- Dota 2 Addon for Creep Block Episodic Reinforcement Learning☆36Updated 7 years ago
- ☆14Updated 6 years ago
- Deep reinforcement learning using an asynchronous advantage actor-critic (A3C) model.☆66Updated 6 years ago
- Dota 2 Python AI☆97Updated 5 years ago
- PyDota2 Framework Integrated with DotaService☆25Updated 5 years ago
- A TensorFlow implementation of DeepMind's A Distributional Perspective on Reinforcement Learning.(C51-DQN)☆56Updated 7 years ago
- starter kit for vizdoom2018-singleplayer track☆27Updated 6 years ago
- ☆117Updated 4 years ago
- Add-on for OpenAI Gym that supports automatic downloading of user environments.☆45Updated 7 years ago
- ☆57Updated last year
- Convert sc2 environment to gym-atari and play some mini-games☆21Updated 6 years ago
- Simplest Version of playing Atari with Deep Q Learning in Tensorflow☆160Updated 6 years ago
- This is the code for "OpenAI Five vs DOTA 2 Explained" By Siraj Raval on Youtube☆154Updated 6 years ago
- A TensorFlow based implementation of the DeepMind Atari playing "Deep Q Learning" agent that works reasonably well☆91Updated 7 years ago
- PySC2 OpenAI Gym Environments☆48Updated 5 years ago
- ☆78Updated 6 years ago
- Fictitious Self-play & Reinforcement Learning☆19Updated 6 years ago
- Duel_DDQN (Dueling Network Architectures + Double DQN) using Keras☆32Updated 8 years ago
- An implementation of Deep Q-Network using Caffe☆67Updated 8 years ago
- Implementations of deep RL papers and random experimentation☆177Updated 6 years ago
- ☆39Updated 6 years ago
- ☆33Updated 6 years ago
- Keras implementation of DQN on ViZDoom environment☆53Updated 7 years ago
- Implementing reinforcement-learning algorithms for pysc2 -environment☆89Updated 6 years ago
- distributed RL spaghetti al arabiata☆26Updated 5 years ago
- ☆30Updated 6 years ago
- Using Asynchronous Deep Reinforcement Learning to play Flappy Bird from pixel input.☆30Updated 7 years ago
- ☆53Updated 7 years ago
- Combining deep learning and reinforcement learning.☆81Updated 2 years ago