Stars
OpenSpiel is a collection of environments and algorithms for research in general reinforcement learning and search/planning in games.
🏆 AI² Tournament RL Agent - Developed for a 1v1 fighting game, featuring multiple reward functions and trained AI models
Reinforcement Learning / AI Bots in Card (Poker) Games - Blackjack, Leduc, Texas, DouDizhu, Mahjong, UNO.
Multi-dimensional Chebyshev tensor interpolation with analytical derivatives for .NET
Cross-sectional Transformer and FFN for stock return prediction and alpha generation. Implements GKX (2020) NN5 replication and MSRR loss (Kelly et al. 2025) for direct portfolio Sharpe optimizatio…
Universal code structure visualization via static analysis — tree-sitter powered, no LLM
Anti-hallucination research mode for Claude Code. Toggle on/off to enforce citation requirements and source grounding.
Causal factor graph + agentic sentiment engine for quant finance. 52-node graph with Claude/GPT analysis, 3D visualization, regime detection, and signal propagation.
Document intelligence system for credit agreement PDFs — extracts 44 structured fields, validates with citation verification, and generates deal-type-aware risk scores
[NeurIPS 2024] Temporal-Difference Learning Using Distributed Error Signals
High Performance Computation for N-D Tensors in .NET, similar API to NumPy.
Fast multi-dimensional Chebyshev tensor interpolation with analytical derivatives. Barycentric interpolation via BLAS GEMV, Sliding Technique, and Tensor Train (TT-Cross) for 5+ dimensions.
Black Scholes calculator for Python (up to 3rd order Greeks)
Official implementation of MCVD: Masked Conditional Video Diffusion for Prediction, Generation, and Interpolation (https://arxiv.org/abs/2205.09853)
PyTorch-based framework for Deep Hedging
XuanCe: A Comprehensive and Unified Deep Reinforcement Learning Library
A collection of multi agent environments based on OpenAI gym.
Implementation of 5-factor Fama French Model
🔍 An LLM-based Multi-agent Framework of Web Search Engine (like Perplexity.ai Pro and SearchGPT)
Leveraging BERT and c-TF-IDF to create easily interpretable topics.