Fresh daily
AI News
Latest AI tool releases, research breakthroughs, and industry news.
Older
Meta-learning for wrestling
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.
Nonlinear computation in deep linear networks
Learning to model other minds
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.
Learning with opponent-learning awareness
More on Dota 2
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
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.
Better exploration with parameter noise
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
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.
Robust adversarial inputs
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
Teacher–student curriculum learning
Learning from human preferences
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
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.
UCB exploration via Q-ensembles
Robots that learn
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.
Equivalence between policy gradients and soft Q-learning
Stochastic Neural Networks for hierarchical reinforcement learning
Unsupervised sentiment neuron
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.
Spam detection in the physical world
We’ve created the world’s first Spam-detecting AI trained entirely in simulation and deployed on a physical robot.
Evolution strategies as a scalable alternative to reinforcement learning
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.