Tag

This paper introduces ReAct, an approach that integrates reasoning and acting in large language models (LLMs). ReAct enables LLMs to generate both reasoning traces and task-specific actions in an interleaved manner. This synergy allows reasoning to help induce, track, and update action plans, while actions interface with external sources like knowledge bases to gather more information, overcoming issues of hallucination and error propagation in prior methods.

Orchestrates and scales Python-based AI/ML workloads from laptop to thousands of GPUs — exposing task and actor primitives plus high-level libraries for training, hyperparameter tuning, serving, RL, and data processing. Designed for heterogeneous accelerators and production ML pipelines.

Provides 150+ executed Jupyter notebooks and code that reproduce the book 'Machine Learning for Algorithmic Trading (2nd ed.)' — covers feature engineering, alternative-data signal extraction, backtesting, NLP, deep learning and reinforcement learning for trading; best for quant researchers and practitioners.

CleanRL is a high-quality, single-file implementation library for deep reinforcement learning (Deep RL). It provides compact, research-friendly standalone implementations of many RL algorithms (PPO, DQN, C51, DDPG, TD3, SAC, PPG, etc.), benchmarks, TensorBoard logging, Weights & Biases integration, and cloud/run tooling. It emphasizes readability, reproducibility, and ease of understanding rather than being a modular importable framework.

Provides a modular PyTorch-based reinforcement learning library with dual high-level and procedural APIs — supporting online/offline, model-based and multi-agent algorithms, vectorized environments, and configurable training pipelines for research and engineering.

An AI-native, weight-centric infrastructure for quantitative trading that produces target portfolio weight vectors to unify data ingestion, strategy composition, backtesting, and live/broker execution. Modular pipeline supports ML/DRL allocators, LLM-ready preprocessing, multi-source data, and Alpaca integration for paper/live trading.

Qlib is an open-source, AI-oriented quantitative investment platform from Microsoft that provides a full pipeline for quant research — data processing, feature engineering, model training, backtesting and serving. It supports supervised learning, market-dynamics modeling and reinforcement learning, and integrates tools (e.g., RD-Agent) for automated factor mining and model optimization.

Provides GPU-accelerated simulation and ready-to-train robot-learning environments (RL, imitation, motion planning) built on NVIDIA Isaac Sim. Includes RTX-based sensors, LIDAR, 30+ environments and 16+ robot models, and supports local or distributed runs for sim-to-real workflows.

Provides human preference comparison pairs and red-team conversation transcripts collected by Anthropic for training preference/reward models and studying harmful model behaviors; intended for RLHF and safety research, not for supervised fine-tuning of dialogue agents.

Provides a scalable RLHF framework combining Ray, vLLM and DeepSpeed for distributed training and high-throughput generation. Uses an agent-based token-in-token-out execution, ships PPO/REINFORCE++ variants, and supports VLMs—suited for large-scale RLHF experiments and production pipelines.

Hardware-agnostic PyTorch robotics library: unified Robot API, LeRobotDataset (Parquet + MP4) for synchronized video+state, and ready-to-train policies (imitation, RL, VLA) with Hugging Face Hub dataset/model integration.

Hands-on coding tutorial series for large language models with slides and runnable notebooks covering fine-tuning, prompting, RLHF, safety, steganography, watermarking, multimodal models, GUI agents, and deployment. Community-maintained, free course materials for students and researchers.