Policy page 43

OpenAI News April 21, 2017 07:00

Equivalence between policy gradients and soft Q-learning

Two of the leading approaches for model-free reinforcement learning are policy gradient methods and Q-learning methods. Q-learning methods can be effective and sample-efficient when they work, however, it is not well-understood why they work, since...

Topics: Policy

Entities: Policy Target

OpenAI News April 10, 2017 07:00

Stochastic Neural Networks for hierarchical reinforcement learning

Deep reinforcement learning has achieved many impressive results in recent years. However, tasks with sparse rewards or long horizons continue to pose significant challenges. To tackle these important problems, we propose a general framework that first...

Topics: Policy Infrastructure

Entities: Policy Infrastructure

OpenAI News February 08, 2017 08:00

Adversarial attacks on neural network policies

Machine learning classifiers are known to be vulnerable to inputs maliciously constructed by adversaries to force misclassification. Such adversarial examples have been extensively studied in the context of computer vision applications. In this work, we...

Topics: Policy Infrastructure

Entities: Policy Infrastructure

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...

Topics: Models Policy Infrastructure

Entities: 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...

Topics: Policy

Entities: Policy Google