# Simulator

Nous Research focuses on developing human-centered language models and simulators, aimed at aligning AI systems with real-world user experiences. Our primary research areas include model architecture, data synthesis, fine-tuning, and inference. We prioritize the development of open-source, human-compatible models, challenging traditional closed model approaches.

UniSim is a product for learning interactive, real-world simulators. It simulates the behavior of humans, robots, and other types of interactive agents through generative modeling, producing realistic experiences. UniSim can be used for creating controllable content in games and movies, as well as training agents in simulations that can be directly deployed to the real world. UniSim is trained using diverse datasets to mimic the visual results of high-level commands and low-level control. It can be used to train high-level visual language planners and low-level reinforcement learning strategies, demonstrating significant transfer effects in the real world. UniSim can also be applied to other types of intelligent tasks, such as video captioning and detection models. Through UniSim, users can perform long-term planning, reinforcement learning, and decision optimization.

Octopus is an environment-based visual language programming tool that can efficiently parse agents' visual and textual task goals, formulate complex action sequences, and generate executable code. Octopus is designed to enable agents to handle a wide range of tasks, from everyday chores in simulators to complex interactions in complex video games. Octopus is trained in our experimental environment OctoVerse by leveraging GPT-4 to control the exploration agent, generating training data in the form of action blueprints and corresponding executable code. We also collect feedback to enable a reinforcement learning with environment feedback (RLEF) training paradigm. Through a series of experiments, we elucidate Octopus' capabilities and present compelling results, demonstrating that the proposed RLEF approach effectively enhances agent decision-making. By open-sourcing our model architecture, simulator, and dataset, we aim to foster innovation and promote collaborative applications within the broader AI community.

AI Town is a virtual town where AI characters live, chat, and socialize. It's a deployable starter kit that can be easily used to build and customize your own version of AI Town. It features a powerful backend engine that supports shared global state, transactions, and recording of all events, suitable for projects ranging from simple to scalable multiplayer games. It also provides a JS/TS framework for customization and extension.

CreditHQ X Sttabot is a credit score simulator that demonstrates how your credit score varies across different case scenarios and provides corresponding advice. The product features a simple, easy-to-use functionality and a user-friendly interface, helping users easily understand the factors influencing their credit score. Pricing information can be found on the official website.