Pinned Repositories
imitation
Clean PyTorch implementations of imitation and reward learning algorithms
minerl
MineRL Competition for Sample Efficient Reinforcement Learning - Python Package
cuad
CUAD (NeurIPS 2021)
pedestrian_prediction
realtime, confidence-varying trajectory prediction for "Probabilistically Safe Robot Planning with Confidence-Based Human Predictions". RSS '18
VillageDivinatorPlugin
output village coordinates
tcpdump
the TCPdump network dissector
maud
shwang's Repositories
shwang/pedestrian_prediction
realtime, confidence-varying trajectory prediction for "Probabilistically Safe Robot Planning with Confidence-Based Human Predictions". RSS '18
shwang/cuad
CUAD (NeurIPS 2021)
shwang/VillageDivinatorPlugin
output village coordinates
shwang/adversarial-finetuning
shwang/baselines
OpenAI Baselines: high-quality implementations of reinforcement learning algorithms
shwang/beir
A Heterogeneous Benchmark for Information Retrieval. Easy to use, evaluate your models across 15+ diverse IR datasets.
shwang/causal-text-embeddings-tf2
Tensorflow 2 implementation of Causal-BERT
shwang/count_pile_name_freq
shwang/CrossAttentionControl
Unofficial implementation of "Prompt-to-Prompt Image Editing with Cross Attention Control" with Stable Diffusion
shwang/FasterTransformer
Transformer related optimization, including BERT, GPT
shwang/github-actions-for-packages
shwang/imitation-extern
CHAI's imitation repo + benchmarking against SB GAIL
shwang/inverse_rl
shwang/langchain
⚡ Building applications with LLMs through composability ⚡
shwang/mc_scripts
Tooling
shwang/minerl
MineRL Competition for Sample Efficient Reinforcement Learning - Python Package
shwang/MOTD-swapper
shwang/mujoco-py
MuJoCo is a physics engine for detailed, efficient rigid body simulations with contacts. mujoco-py allows using MuJoCo from Python 3.
shwang/polyjuice
shwang/QMSum
Dataset for NAACL 2021 paper: "QMSum: A New Benchmark for Query-based Multi-domain Meeting Summarization"
shwang/restic-systemd-automatic-backup
My restic backup solution using Backblaze B2 storage, systemd timers (or cron) and email notifications on failure.
shwang/rllab
rllab is a framework for developing and evaluating reinforcement learning algorithms, fully compatible with OpenAI Gym.
shwang/roam42
Level up Roam with power user features. Automation, keyboard nav, dictionary, live preview and more.
shwang/sacred
Sacred is a tool to help you configure, organize, log and reproduce experiments developed at IDSIA.
shwang/shwang.github.io
shwang/simple_bc_baseline
shwang/Sphinx-Autosummary-Recursion
Demonstrating the new automatic package recursion facility in sphinx.ext.autosummary version 3.1
shwang/stable-baselines3
PyTorch version of Stable Baselines, improved implementations of reinforcement learning algorithms.
shwang/stablediffusion
High-Resolution Image Synthesis with Latent Diffusion Models
shwang/vat-pytorch
Virtual Adversarial Training (VAT) techniques in PyTorch