Our latest robotics techniques allow robot controllers, trained entirely in simulation and deployed on physical robots, to react to unplanned changes in the environment as they solve simple tasks. That is, we’ve used these techniques to build closed-loop systems rather than open-loop ones as before.
AI 速览 Asymmetric actor critic方法被提出用于基于图像的机器人学习。
AI 速览 英伟达等机构提出动力学随机化方法,通过在仿真训练中随机化机器人动力学参数,实现无需真实数据微调的仿真到现实控制策略迁移。
AI 速览 深度线性网络可执行非线性计算。
AI 速览 提出“对手学习感知”学习方法,使智能体在博弈中考虑对手的学习行为以优化策略。
We’re releasing two new OpenAI Baselines implementations: ACKTR and A2C. A2C is a synchronous, deterministic variant of Asynchronous Advantage Actor Critic (A3C) which we’ve found gives equal performance. ACKTR is a more sample-efficient reinforcement learning algorithm than TRPO and A2C, and requires only slightly more computation than A2C per update.
We’ve found that adding adaptive noise to the parameters of reinforcement learning algorithms frequently boosts performance. This exploration method is simple to implement and very rarely decreases performance, so it’s worth trying on any problem.
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 reinforcement learning algorithm at OpenAI because of its ease of use and good performance.
We’ve created images that reliably fool neural network classifiers when viewed from varied scales and perspectives. This challenges a claim from last week that self-driving cars would be hard to trick maliciously since they capture images from multiple scales, angles, perspectives, and the like.
AI 速览 OpenAI提出Hindsight Experience Replay,一种通过将失败经验重新标记为目标来实现高效强化学习的方法。
AI 速览 教师-学生课程学习
We’re open-sourcing a high-performance Python library for robotic simulation using the MuJoCo engine, developed over our past year of robotics research.
UCB exploration via Q-ensembles
We’re open-sourcing OpenAI Baselines, our internal effort to reproduce reinforcement learning algorithms with performance on par with published results. We’ll release the algorithms over upcoming months; today’s release includes DQN and three of its variants.
We’ve created a robotics system, trained entirely in simulation and deployed on a physical robot, which can learn a new task after seeing it done once.
We are releasing Roboschool: open-source software for robot simulation, integrated with OpenAI Gym.
AI 速览 政策梯度与软Q学习之间存在等价性。
AI 速览 随机神经网络被用于分层强化学习。
We’ve developed an unsupervised system which learns an excellent representation of sentiment, despite being trained only to predict the next character in the text of Amazon reviews.
We’ve discovered that evolution strategies (ES), an optimization technique that’s been known for decades, rivals the performance of standard reinforcement learning (RL) techniques on modern RL benchmarks (e.g. Atari/MuJoCo), while overcoming many of RL’s inconveniences.
AI 速览 单样本模仿学习(One-shot imitation learning)指智能体仅通过一个演示样本即可学习并复现新任务,无需大量重复训练数据。
We’re excited to support today’s launch of Distill, a new kind of journal aimed at excellent communication of machine learning results (novel or existing).
AI 速览 第三人称模仿学习。
AI 速览 对抗性攻击可针对神经网络策略,威胁强化学习智能体的决策安全。
AI 速览 OpenAI提出PixelCNN++,通过离散化逻辑混合似然及其他改进优化PixelCNN。
Reinforcement learning algorithms can break in surprising, counterintuitive ways. In this post we’ll explore one failure mode, which is where you misspecify your reward function.
AI 速览 研究探讨了基于计数的探索方法在深度强化学习中的应用。
We’re working with Microsoft to start running most of our large-scale experiments on Azure.
AI 速览 RL²提出通过慢速强化学习实现快速强化学习,即用慢速RL训练一个循环神经网络作为快速RL算法,使其能在新任务上快速适应。
AI 速览 变分有损自编码器(Variational Lossy Autoencoder)是一种结合变分自编码器与有损压缩思想的方法,旨在学习数据的紧凑表示。