Policy page 42

OpenAI News July 10, 2019 07:00

Why responsible AI development needs cooperation on safety

We’ve written a policy research paper identifying four strategies that can be used today to improve the likelihood of long-term industry cooperation on safety norms in AI: communicating risks and benefits, technical collaboration, increased transparency,...

Topics: Policy

Entities: Policy

OpenAI News February 19, 2019 08:00

AI safety needs social scientists

We’ve written a paper arguing that long-term AI safety research needs social scientists to ensure AI alignment algorithms succeed when actual humans are involved. Properly aligning advanced AI systems with human values requires resolving many uncertainties...

Topics: Models Policy

Entities: OpenAI Models Policy

OpenAI News October 22, 2018 07:00

Learning complex goals with iterated amplification

We’re proposing an AI safety technique called iterated amplification that lets us specify complicated behaviors and goals that are beyond human scale, by demonstrating how to decompose a task into simpler sub-tasks, rather than by providing labeled data or...

Topics: Policy

Entities: Policy

OpenAI News July 26, 2018 07:00

Variational option discovery algorithms

We explore methods for option discovery based on variational inference and make two algorithmic contributions. First: we highlight a tight connection between variational option discovery methods and variational autoencoders, and introduce Variational...

Topics: Policy Infrastructure

Entities: Policy Infrastructure

OpenAI News June 17, 2018 07:00

Learning policy representations in multiagent systems

Modeling agent behavior is central to understanding the emergence of complex phenomena in multiagent systems. Prior work in agent modeling has largely been task-specific and driven by hand-engineering domain-specific prior knowledge. We propose a general...

Topics: Policy

Entities: Policy

OpenAI News May 03, 2018 07:00

AI safety via debate

We’re proposing an AI safety technique which trains agents to debate topics with one another, using a human to judge who wins.

Topics: Agents Policy

Entities: Agents Policy

OpenAI News April 18, 2018 07:00

Evolved Policy Gradients

We’re releasing an experimental metalearning approach called Evolved Policy Gradients, a method that evolves the loss function of learning agents, which can enable fast training on novel tasks. Agents trained with EPG can succeed at basic tasks at test time...

Topics: Agents Policy Infrastructure

Entities: Agents Policy Infrastructure

OpenAI News March 20, 2018 07:00

Variance reduction for policy gradient with action-dependent factorized baselines

Policy gradient methods have enjoyed great success in deep reinforcement learning but suffer from high variance of gradient estimates. The high variance problem is particularly exasperated in problems with long horizons or high-dimensional action spaces. To...

Topics: Policy

Entities: Policy Target

OpenAI News October 18, 2017 07:00

Asymmetric actor critic for image-based robot learning

Deep reinforcement learning (RL) has proven a powerful technique in many sequential decision making domains. However, Robotics poses many challenges for RL, most notably training on a physical system can be expensive and dangerous, which has sparked...

Topics: Policy Infrastructure

Entities: Policy Infrastructure

OpenAI News September 13, 2017 07:00

Learning with opponent-learning awareness

Multi-agent settings are quickly gathering importance in machine learning. This includes a plethora of recent work on deep multi-agent reinforcement learning, but also can be extended to hierarchical RL, generative adversarial networks and decentralised...

Topics: Agents Policy Infrastructure

Entities: Agents Policy Infrastructure

OpenAI News July 20, 2017 07:00

Proximal Policy Optimization

We’re releasing a new class of reinforcement learning algorithms, Proximal Policy Optimization (PPO), which perform comparably or better than state-of-the-art approaches while being much simpler to implement and tune. PPO has become the default...

Topics: Models Policy

Entities: OpenAI Models Policy

OpenAI News July 05, 2017 07:00

Hindsight Experience Replay

Dealing with sparse rewards is one of the biggest challenges in Reinforcement Learning (RL). We present a novel technique called Hindsight Experience Replay which allows sample-efficient learning from rewards which are sparse and binary and therefore avoid...

Topics: Policy

Entities: Policy