A simple, yet elegant, HTTP library.

Clean baseline implementation of PPO using an episodic TransformerXL memory

PyTorch implementation of the state-of-the-art distributional reinforcement learning algorithm Fully Parameterized Quantile Function (FQF) and Extensions: N-step Bootstrapping, PER, Noisy Layer, Du…

PyTorch Implementation of Ape-X (Distributed prioritized experience replay) architecture with DQN learner

The most simple, flexible, and comprehensive OpenAI Gym trading environment (Approved by OpenAI Gym)