Chenjia Bai

Tensorflow-TCN. Tensorflow eager implementation of Temporal Convolutional Network (TCN)

PBRL. Pessimistic Bootstrapping for Uncertainty-Driven Offline Reinforcement Learning

COPO. Online Preference Alignment for Language Models via Count-based Exploration

GHER. G-HER algorithm

UTDS. Pessimistic Value Iteration for Multi-Task Data Sharing in Offline RL

MINE. Mutual Information Neural Estimation (Pytorch)

Pix2Pix-eager. Tensorflow eager implementation of Pix2Pix (Image-to-image translation with conditional adversarial networks)

Contrastive-UCB. Contrastive UCB: Provably Efficient Contrastive Self-Supervised Learning in Online Reinforcement Learning

OB2I. Code for "Principled Exploration via Optimistic Bootstrapping and Backward Induction"

MQN-offline. Monotonic Quantile Network for Worst-Case Offline Reinforcement Learning

BHER. Code for "Addressing Hindsight Bias in Multi-Goal Reinforcement Learning"

Gumbel-softmax. Tensorflow eager for "categorical variational autoencoder using the Gumbel-Softmax estimator"

CeSD. Constrained Ensemble Exploration for Unsupervised Skill Discovery

NMT-eager. tensorflow implementation of neural machine translation with attention

DB. Dynamic Bottleneck for Robust Self-Supervised Exploration

Resnet. tensorflow implementation of Resnet50 with tf.keras.model and eager

VDM. Code for "Variational Dynamic for Self-Supervised Exploration in Deep Reinforcement Learning"

Graduation-design. Python

CycleGAN-eager. Tensorflow implementation of CycleGAN "Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks"

DeepLearning-Self_Driving. DeepLearning for self driving cars

CIFAR-10-basic. using basic neural network and softmax/SVM loss function to classify the CIFAR-10 image set

mc-dropout. Tensorflow eager code for mc dropout. [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning]

Segmentation-keras. Keras implementation of "Multi-scale context aggregation by dilated convolutions (ICLR 2016)"

Non-local-nets-tensorflow. Implementation of "Non-local neural networks." (CVPR 18) with tensorflow eager execution.

IMDB-eager. tensorflow implementation of IMDB dataset classification

BeCL-MI-Entropy. Mutual Information and Entropy estimation of BeCL and baseline methods

C3D-tensorflow-eager. Implement C3D model for video recognition proporsed in "Learning Spatiotemporal Features with 3D Convolutional Networks"

Mnist-tf-eager. Mnist classification with tensorflow eager execution

TD3. The basic implementation of TD3/DDPG algorithm with Tensorflow 2

offline_safe_rl. Python

Embodied-Survey. Figures for Embodied Survey

DCGAN-eager. Tensorflow eager implementation of "DCGAN"

VAEAC. Tensorflow version of Variational Autoencoder with Arbitrary Conditioning

probabilistic-ensemble. Python

DRAW_RNN_ImageGeneration. TensorFlow Implementation of "DRAW: A Recurrent Neural Network For Image Generation"

Style-transfer. Neural Style Transfer with tensorflow eager

cluster-code. Python

NeuralTuringMachine. Tensorflow implementation of a Neural Turing Machine (simple version)

RNN-Sequential-Mnist. Tensorflow eager implementation to solving Sequential-Mnist classification problem using Recurrent Neural network

PTB-eager. tensorflow implementation of language model in PTB dataset

Leetcode_train. Leetcode coded by me

Transformer. Basic implementation of Transformer model (Attention is all you need) with Tensorflow eager

BreakOut-A3C. A3C method in Breakout game

VAE-basic. tensorflow and keras for variational auto-encoder (VAE) model

noreward-rl. [ICML 2017] TensorFlow code for Curiosity-driven Exploration for Deep Reinforcement Learning