georgepsh's repositories
ModelDistillation
BiLSTM Distillation with BERT for Sequence CLassification
MountainCarContinuous-v0_DDGP
DDPG solution for MountainCarContinuous problem
dqn-pytorch
DQN to play Atari Pong
NeuralStyleTransfer
Neural Style Transfer Pytorch Implementation
expert
Expert-augmented actor-critic
GIQA
Pytorch implementation of Generated Image Quality Assessment
MLBD
Materials for "Machine Learning on Big Data" course
MountainCar-v0_DQN
DQN solution for Open AI's MountainCar-v0 problem
pytorch-a2c-ppo-acktr-gail
PyTorch implementation of Advantage Actor Critic (A2C), Proximal Policy Optimization (PPO), Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation (ACKTR) and Generative Adversarial Imitation Learning (GAIL).
ray
An open source framework that provides a simple, universal API for building distributed applications. Ray is packaged with RLlib, a scalable reinforcement learning library, and Tune, a scalable hyperparameter tuning library.
stable-baselines
A fork of OpenAI Baselines, implementations of reinforcement learning algorithms