curiosity-driven

Tag

Cards List
#curiosity-driven

Reinforcement learning with prediction-based rewards

OpenAI Blog · 2018-10-31 Cached

OpenAI introduces Random Network Distillation (RND), a prediction-based method for encouraging exploration in RL agents through curiosity, achieving human-level performance on Montezuma's Revenge without demonstrations or game state access.

0 favorites 0 likes
← Back to home

Submit Feedback