Policy

OpenAI News · October 11, 2016 07:00

Transfer from simulation to real world through learning deep inverse dynamics model

Developing control policies in simulation is often more practical and safer than directly running experiments in the real world. This applies to policies obtained from planning and optimization, and even more so to policies obtained from reinforcement...

Models Policy Infrastructure

Models Policy Infrastructure

OpenAI News · June 21, 2016 07:00

Concrete AI safety problems

We (along with researchers from Berkeley and Stanford) are co-authors on today’s paper led by Google Brain researchers, Concrete Problems in AI Safety. The paper explores many research problems around ensuring that modern machine learning systems operate as...

Policy

Policy Google