Yura Burda
Yura Burda

Yura Burda

Harri Edwards Yura Burda

Reinforcement Learning with Prediction-Based Rewards

We’ve developed Random Network Distillation (RND), a prediction-based method for encouraging reinforcement learning agents to explore their environments through curiosity, which for the first time exceeds average human performance on Montezuma’s Revenge.

Igor Mordatch Ilya Sutskever Maruan Al-Shedivat Pieter Abbeel Trapit Bansal Yura Burda

Meta-Learning for Wrestling

We show that for the task of simulated robot wrestling, a meta-learning agent can learn to quickly defeat a stronger non-meta-learning agent.

Igor Mordatch Ilya Sutskever Maruan Al-Shedivat Pieter Abbeel Trapit Bansal Yura Burda

Meta-Learning for Wrestling

We show that for the task of simulated robot wrestling, a meta-learning agent can learn to quickly defeat a stronger non-meta-learning agent.