Deep Reinforcement Learning Codes

Currently there are only the codes for distributional reinforcement learning here. Codes for algorithms: DQN, C51, QR-DQN, IQN, QUOTA.

Thanks to sungyubkim and Shangtong Zhang!

A lot of my codes references their implementations.

Always up for a chat -- shoot me an email if you'd like to discuss anything!

Dependency:

• pytorch(>=1.0.0)

• gym(=0.10.9)

• numpy

• matplotlib

Usage:

When your computer's python environment satisfies the above dependencies, you can run the code. For example, enter:

python 4_iqn.py Breakout

on the command line to run the algorithms in the Atari environment. You can change some specific parameters for the algorithms inside the codes.

References:

1. Human-level control through deep reinforcement learning(DQN) [Paper] [Code]

2. A Distributional Perspective on Reinforcement Learning(C51) [Paper] [Code]

3. Distributional Reinforcement Learning with Quantile Regression(QR-DQN) [Paper] [Code]

4. Implicit Quantile Networks for Distributional Reinforcement Learning(IQN) [Paper] [Code]

5. QUOTA: The Quantile Option Architecture for Reinforcement Learning(QUOTA) [Paper] [Code]