Atari - Deep Reinforcement Learning algorithms in TensorFlow
MIT License
Learning to play Atari in TensorFlow using Deep Reinforcement Learning
git clone https://github.com/brendanator/atari-rl
git submodule update --init
conda create --name atari-rl python=3.5
source activate atari-rl
conda install -y -c https://conda.binstar.org/menpo opencv3
conda install -y h5py numpy
pip install tensorflow
pip install 'gym[atari]'
Python 2.7 is also supported
python main.py --help
python main.py --game Breakout
python main.py
python main.py --double_q
python main.py --dueling
python main.py --optimality_tightening
python main.py --replay_prioritized
python main.py --exploration_bonus
python main.py --bootstrapped
python main.py --persistent_advantage_learning
python main.py --reward_scaling
python main.py --async one_step
python main.py --async n_step
python main.py --async n_step --sarsa
python main.py --async a3c