Chenjia Bai

Pessimistic Bootstrapping for Uncertainty-Driven Offline Reinforcement Learning

Tensorflow eager implementation of Temporal Convolutional Network (TCN)

Online Preference Alignment for Language Models via Count-based Exploration

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

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

Dynamic Bottleneck for Robust Self-Supervised Exploration

G-HER algorithm

Mutual Information Neural Estimation (Pytorch)

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

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

Monotonic Quantile Network for Worst-Case Offline Reinforcement Learning

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

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

Constrained Ensemble Exploration for Unsupervised Skill Discovery

tensorflow implementation of neural machine translation with attention

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

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

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

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

No description.

The code implementation of EmbodiedAI-Book

DeepLearning for self driving cars

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

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

Rainbow: Combining Improvements in Deep Reinforcement Learning

Mutual Information and Entropy estimation of BeCL and baseline methods

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

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

tensorflow implementation of IMDB dataset classification

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

Figures for Embodied Survey

The basic implementation of TD3/DDPG algorithm with Tensorflow 2

No description.

No description.

Tensorflow version of Variational Autoencoder with Arbitrary Conditioning

Tensorflow eager implementation of "DCGAN"

Neural Style Transfer with tensorflow eager

[ICLR 2018] TensorFlow code for zero-shot visual imitation by self-supervised exploration

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

Accompanying repository for Let's make a DQN / A3C series.

This repository contains the code to implement the Hierarchical Actor-Critic (HAC) algorithm.

Activation Maps (Layers Outputs) and Gradients in Keras.

Code for the paper "Large-Scale Study of Curiosity-Driven Learning"

[ICML 2019] TensorFlow Code for Self-Supervised Exploration via Disagreement

A3C method in Breakout game

Mnist classification with tensorflow eager execution

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

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

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

Tensorflow implementation of a Neural Turing Machine (simple version)

tensorflow implementation of language model in PTB dataset

Leetcode coded by me

No description.

github pages

具身智能书籍相关代码

test of lerobot dataset

Training a humanoid robot for locomotion using Reinforcement Learning

SELM

HumanPlus: Humanoid Shadowing and Imitation from Humans

BeCL: Behavior Contrastive Learning for Unsupervised Skill Discovery.

No description.

Code for "Temporal Difference Learning for Model Predictive Control"

[CoRL 2023] Robot Parkour Learning

CLIPort: What and Where Pathways for Robotic Manipulation

Sim-to-real RL training and deployment tools for the Unitree Go1 robot.

No description.

Reproduce for "Sample-Efficient Deep Reinforcement Learning via Episodic Backward Update" (NeurIPS 2019) with Tensorflow

No description.

No description.

Offline Risk-Averse Actor-Critic (O-RAAC). A model-free RL algorithm for risk-averse RL in a fully offline setting

SunRise-Constrain

SUNRISE: A Simple Unified Framework for Ensemble Learning in Deep Reinforcement Learning

No description.

Rebuttal of OEB3

Efficient Exploration through Bayesian Deep Q-Networks

Curiosity Bottleneck in Self-Supervised Learning Setting

Keras implementation of Representation Learning with Contrastive Predictive Coding

The basic algorithm of policy gradients

Reinforcement Learning implementations and research prototyping in TensorFlow

Basic use of stable baselines for reinforcement learning

No description.

Tensorflow implementation of Bayesian linear regression (Weight Uncertainty in Neural Networks)

Tensorflow implementation of Image Caption with Attention

A basic LaTeX template document for creating journal response to reviewers letters