- Python 3.9.13 (or higher)
- torch 1.13.1+cu116
- After unzipping Roms.zip, ingrain it into python. This is feasible by running "python -m atari_py.import_roms". If successful, it is listed by "print(atari_py.list_games())".
- contains basic usage of deep neural networks based on pytorch.
- This includes 1) regression, 2) logistic regression, 3) sine-curve matching.
- contains well-known examples of basic Deep Q Learning, starting from 0) template of neural network.
- This includes 1) cartpole, 2) mountain car examples.
- contains wrappers that contain necessary functions.
- Every method has (method).py and (method_observe).py, each of which is for training the model and demostrating the play of the model.
- (Mnih et al., 2015) Human-level control through deep reinforcement learning
- (Bellemare et al., 2017a) Distributional perspective on reinforcement learning
- (Dabney et al., 2018b) Distributional reinforcement learning with quantile regression
- (Dabney et al., 2018a) Implicit quantile networks for distributional reinforcement learning
- (Nguyen et al., 2021) Distributional reinforcement learning via moment matching