← Latest products

RL agent trained only in synthetic markets got better on real 2020crash

An RL agent trained only in synthetic markets got better at hedging the real 2020 and 2022 crashes.

Open source

5 stars · GitHubexternal site

Visit github.comexternal site

Reactions (1)

Similar products

by description similarity

  1. RULER

    openpipe.ai

    Easily apply RL to any agent

    Hacker News81 pts

  2. I RL-trained an agent that trains models with RL (for ~$1.3k)

    github.com

    RL-training an AI agent to RL-train AI agents.

    Hacker News107 pts

  3. Terminal-Bench-RL

    github.com

    Training long-horizon terminal agents with RL

    Hacker News125 pts

  4. ART

    github.com

    a new open-source RL framework for training agents

    Hacker News116 pts

  5. I built an AI agent that helps me invest

    github.com

    Build effective agents using Model Context Protocol and simple workflow patterns

    Hacker News80 pts