OpenAI

Source: https://openai.com

Found 1065 news

  • Sim-to-real transfer of robotic control with dynamics randomization
    OpenAI - 07:00 Oct 18, 2017
  • Asymmetric actor critic for image-based robot learning
    OpenAI - 07:00 Oct 18, 2017
  • Domain randomization and generative models for robotic grasping
    OpenAI - 07:00 Oct 17, 2017
  • Meta-learning for wrestling
    OpenAI - 07:00 Oct 11, 2017
    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, and also show that the meta-learning agent can adapt to physical malfunction.
  • Competitive self-play
    OpenAI - 07:00 Oct 11, 2017
    We’ve found that self-play allows simulated AIs to discover physical skills like tackling, ducking, faking, kicking, catching, and diving for the ball, without explicitly designing an environment with these skills in mind. Self-play ensures that the environment is always the right difficulty for an AI to improve. Taken alongside our Dota 2 self-play results, we have increasing confidence that self-play will be a core part of powerful AI systems in the future.
  • Nonlinear computation in deep linear networks
    OpenAI - 07:00 Sep 29, 2017
  • Learning to model other minds
    OpenAI - 07:00 Sep 14, 2017
    We’re releasing an algorithm which accounts for the fact that other agents are learning too, and discovers self-interested yet collaborative strategies like tit-for-tat in the iterated prisoner’s dilemma. This algorithm, Learning with Opponent-Learning Awareness (LOLA), is a small step towards agents that model other minds.
    Tags: Learning
  • Learning with opponent-learning awareness
    OpenAI - 07:00 Sep 13, 2017
  • OpenAI Baselines: ACKTR & A2C
    OpenAI - 07:00 Aug 18, 2017
    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.
    Tags: ACKTR OpenAI Baselines
  • More on Dota 2
    OpenAI - 07:00 Aug 16, 2017
    Our Dota 2 result shows that self-play can catapult the performance of machine learning systems from far below human level to superhuman, given sufficient compute. In the span of a month, our system went from barely matching a high-ranked player to beating the top pros and has continued to improve since then. Supervised deep learning systems can only be as good as their training datasets, but in self-play systems, the available data improves automatically as the agent gets better.
  • Dota 2
    OpenAI - 07:00 Aug 11, 2017
    We’ve created a bot which beats the world’s top professionals at 1v1 matches of Dota 2 under standard tournament rules. The bot learned the game from scratch by self-play, and does not use imitation learning or tree search. This is a step towards building AI systems which accomplish well-defined goals in messy, complicated situations involving real humans.
    Tags: Dota
  • Gathering human feedback
    OpenAI - 07:00 Aug 03, 2017
    RL-Teacher is an open-source implementation of our interface to train AIs via occasional human feedback rather than hand-crafted reward functions. The underlying technique was developed as a step towards safe AI systems, but also applies to reinforcement learning problems with rewards that are hard to specify.
  • Better exploration with parameter noise
    OpenAI - 07:00 Jul 27, 2017
    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.
  • Proximal Policy Optimization
    OpenAI - 07:00 Jul 20, 2017
    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.
    Tags: Proximal Policy Optimization
  • Robust adversarial inputs
    OpenAI - 07:00 Jul 17, 2017
    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.
  • Hindsight Experience Replay
    OpenAI - 07:00 Jul 05, 2017
  • Teacher–student curriculum learning
    OpenAI - 07:00 Jul 01, 2017
  • Faster physics in Python
    OpenAI - 07:00 Jun 28, 2017
    We’re open-sourcing a high-performance Python library for robotic simulation using the MuJoCo engine, developed over our past year of robotics research.
    Tags: Python
  • Learning from human preferences
    OpenAI - 07:00 Jun 13, 2017
    One step towards building safe AI systems is to remove the need for humans to write goal functions, since using a simple proxy for a complex goal, or getting the complex goal a bit wrong, can lead to undesirable and even dangerous behavior. In collaboration with DeepMind’s safety team, we’ve developed an algorithm which can infer what humans want by being told which of two proposed behaviors is better.
  • Learning to cooperate, compete, and communicate
    OpenAI - 07:00 Jun 08, 2017
    Multiagent environments where agents compete for resources are stepping stones on the path to AGI. Multiagent environments have two useful properties: first, there is a natural curriculum—the difficulty of the environment is determined by the skill of your competitors (and if you’re competing against clones of yourself, the environment exactly matches your skill level). Second, a multiagent environment has no stable equilibrium: no matter how smart an agent is, there’s always pressure to get smarter. These environments have a very different feel from traditional environments, and it’ll take a lot more research before we become good at them.

1065 items

Popular Tags