Level-Based Foraging (LBF): A multi-agent reinforcement learning environment

An implementation of model parallel autoregressive transformers on GPUs, based on the DeepSpeed library.

Neural MMO - A Massively Multiagent Environment for Artificial Intelligence Research

Proximal Policy Optimization(PPO) with Intrinsic Curiosity Module(ICM)

This implementation explores two recurrent policies (RIMs versus LSTM) in the context of MARL

Code for structural temporal graph neural networks for anomaly detection in dynamic graphs

This is the code associated with the paper A Variational Inequality Perspective for Generative Adversarial Networks.

MaskedTensors for PyTorch

Simple baselines and RNNs for predicting human motion. Presented at CVPR 17. This pytorch implementation is based on the original one by the authors

Collection of generative models in Tensorflow