Learning Montezuma’s Revenge from a single demonstration
8y
- Published
- Collected
We’ve trained an agent to achieve a high score of 74,500 on Montezuma’s Revenge from a single human demonstration, better than any previously published result. Our algorithm is simple: the agent plays a sequence of games starting from carefully chosen states from the demonstration, and learns from them by optimizing the game score using PPO, the same reinforcement learning algorithm…
overfeed.news indexes and links. We publish a short excerpt — the full article stays at OpenAI News.
More from OpenAI News
Log in to follow this source
Franchisee reconciles cash in 94% less time with ChatGPT Work
An independent Schlotzsky’s and Cinnabon franchisee cut menu repricing time by 95% and built a workflow that could free up $100K in cash flow.
Terminal X matches senior investor judgment 88.6% with GPT-6.1
Terminal X’s Eval Agent grades outputs against a 54-criterion rubric, catching 25% more deviances from a fund’s mandate with GPT-6.1 Sol.
OpenAI acquires Orchestra Bio
OpenAI is acquiring Orchestra Bio to bring AI-powered operations to life sciences R&D, helping biopharma teams accelerate drug development and advance new treatments.
Advancing Coding in Low-Resource Programming Languages
Learn how OpenAI is improving ChatGPT across low-resource programming languages, with new evaluations for software engineering, SQLite, and COBOL migration.