Learning Montezuma’s Revenge from a single demonstration
Agent learns Montezuma's Revenge from a single human demonstration, achieving score of 74,500—better than any previously published result.
Excerpt
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.
Read at source: https://openai.com/index/learning-montezumas-revenge-from-a-single-demonstration