Sponsored by BGRemover - Easily remove image backgrounds online with SharkFoto BGRemover.
BGRemover - Easily remove image backgrounds online with SharkFoto BGRemover.
icon
AI Tools AI Agents MCP AI NewsRanking Submit & Advertise
Login

estrutura PyTorch

  • Learning-to-Communicate-PyTorch

    A PyTorch framework enabling agents to learn emergent communication protocols in multi-agent reinforcement learning tasks.
    0
    0
    What is Learning-to-Communicate-PyTorch?
    This repository implements emergent communication in multi-agent reinforcement learning using PyTorch. Users can configure sender and receiver neural networks to play referential games or cooperative navigation, encouraging agents to develop a discrete or continuous communication channel. It offers scripts for training, evaluation, and visualization of learned protocols, along with utilities for environment creation, message encoding, and decoding. Researchers can extend it with custom tasks, modify network architectures, and analyze protocol efficiency, fostering rapid experimentation in emergent agent communication.
    Learning-to-Communicate-PyTorch Core Features
    • Referential communication game implementation
    • Cooperative navigation task support
    • Modular PyTorch network architectures
    • Discrete and continuous message channels
    • Training, evaluation, and visualization scripts

  • Multi-Agent DDPG with PyTorch & Unity ML-Agents

    Implements decentralized multi-agent DDPG reinforcement learning using PyTorch and Unity ML-Agents for collaborative agent training.
    0
    0
    What is Multi-Agent DDPG with PyTorch & Unity ML-Agents?
    This open-source project delivers a complete multi-agent reinforcement learning framework built on PyTorch and Unity ML-Agents. It offers decentralized DDPG algorithms, environment wrappers, and training scripts. Users can configure agent policies, critic networks, replay buffers, and parallel training workers. Logging hooks allow TensorBoard monitoring, while modular code supports custom reward functions and environment parameters. The repository includes sample Unity scenes demonstrating collaborative navigation tasks, making it ideal for extending and benchmarking multi-agent scenarios in simulation.
Featured