Research

Learning Montezuma’s Revenge from a single demonstration

Source: OpenAI News 04 Jul 2018

Listen to Brief

AI audio in English, based on the NadiAI brief and original source.

Brief

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 that underpins OpenAI Five.

Why It Matters

Keputusan ini menunjukkan keberkesanan pembelajaran dari contoh tunggal dan potensi meningkatkan kecekapan dalam pembelajaran penguatan.

Keep Reading on NadiAI

Selected Related Articles