skypea

FinRL

FinRL: Financial Reinforcement Learning. 🔥

dowhy

DoWhy is a Python library for causal inference that supports explicit modeling and testing of causal assumptions. DoWhy is based on a unified language for causal inference, combining causal graphical models and potential outcomes frameworks.

pytorch-metric-learning

The easiest way to use deep metric learning in your application. Modular, flexible, and extensible. Written in PyTorch.

TransformerLens

A library for mechanistic interpretability of GPT-style language models

CausalDiscoveryToolbox

Package for causal inference in graphs and in the pairwise settings. Tools for graph structure recovery and dependencies are included.

causal-learn

Causal Discovery in Python. It also includes (conditional) independence tests and score functions.

allRank

allRank is a framework for training learning-to-rank neural models based on PyTorch.

causallib

A Python package for modular causal inference analysis and model evaluations

Awesome-LLMs-Evaluation-Papers

The papers are organized according to our survey: Evaluating Large Language Models: A Comprehensive Survey.

representation-engineering

Representation Engineering: A Top-Down Approach to AI Transparency

Causality

GMVAE

Implementation of Gaussian Mixture Variational Autoencoder (GMVAE) for Unsupervised Clustering

causaltune

AutoML for causal inference.

Transformer-Hawkes-Process

Code for Transformer Hawkes Process, ICML 2020.

causaldata

Packages of Example Data for The Effect

causal_learning_unknown_interventions

Code for "Neural causal learning from unknown interventions"

causal_discovery_for_time_series

Causal discovery for time series

torch_truncnorm

Truncated Normal Distribution in PyTorch

cplint

cplint is a suite of programs for reasoning with probabilistic logic programs

example-causal-datasets

Example causal datasets with consistent formatting and ground truth

CausalDynamicsLearning

DAG-NoCurl

DL-abstract-argumentation

Neuro-symbolic approaches to reasoning problems from abstract argumentation

DAG_No_Fear

NeurIPS 2020 Spotlight Paper

argumentation-framework

Prolog Framework for Bipolar Abstract Argumentation

QBAF-Learning

Structure Learning of Gradual Bipolar Argumentation Graphs using Genetic Algorithms

SEP-net

ORLA

ORLA is a symbolic reinforcement learning approach that learns a value-based argumentation framework as a reasoning engine for solving a task. This repo demonstrates ORLA on both the Foggy Frozen Lake and the Takeaway tasks.

ipafair

Reentrant Incremental Argumentation Framework API and solver

IP4AncADMG