Illustration of a crystal snowball
Reinforcement Learning

Simulation Substitutes for Data

The future of machine learning may depend less on amassing ground-truth data than simulating the environment in which a model will operate. Deep learning works like magic with enough high-quality data. When examples are scarce, though, researchers are using simulation to fill the gap.
1 min read
Information related to Implicit Reinforcement without Interaction at Scale (IRIS)
Reinforcement Learning

Different Skills From Different Demos

Reinforcement learning trains models by trial and error. In batch reinforcement learning (BRL), models learn by observing many demonstrations by a variety of actors. But what if one doctor is handier with a scalpel while another excels at suturing?
2 min read
Observational dropout
Reinforcement Learning

Seeing the World Blindfolded

In reinforcement learning, if researchers want an agent to have an internal representation of its environment, they’ll build and train a world model that it can refer to. New research shows that world models can emerge from standard training, rather than needing to be built separately.
2 min read
AlphaGo playing Go with Lee Sedol
Reinforcement Learning

Is AI Making Mastery Obsolete?

Is there any reason to continue playing games that AI has mastered? Ask the former champions who have been toppled by machines.
1 min read
Comparison between TrXL and GTrXL
Reinforcement Learning

Melding Transformers with RL

Large NLP models like BERT can answer questions about a document thanks to the transformer network, a sequence-processing architecture that retains information across much longer sequences than previous methods. But transformers have had little success in reinforcement learning — until now.
2 min read
Bipedal robot crossing obstacles
Reinforcement Learning

Survival of the Overfittest

Neuroevolution, which combines neural networks with ideas drawn from Darwin, is gaining momentum. Its advocates claim that they can achieve faster, better results by generating a succession of new models, each slightly different than its predecessors, rather than relying on a purpose-built model.
2 min read
StarCraft II videogame
Reinforcement Learning

Take That, Humans!

At the BlizzCon gaming convention last weekend, players of the strategy game StarCraft II stood in line to get walloped by DeepMind’s AI. After training for the better part of a year, the bot has become one of the world’s top players.
2 min read
Mechanical hand unscrambling a Rubik's Cube
Reinforcement Learning

Cube Controversy

OpenAI trained a five-fingered robotic hand to unscramble the Rubik’s Cube puzzle, bringing both acclaim and criticism. The AI research lab OpenAI trained a mechanical hand to balance, twist, and turn the cube.
2 min read
Schematic of the architecture used in experiments related to systematic reasoning in deep reinforcement learning
Reinforcement Learning

How Neural Networks Generalize

Humans understand the world by abstraction: If you grasp the concept of grabbing a stick, then you’ll also comprehend grabbing a ball. New work explores deep learning agents’ ability to do the same thing — an important aspect of their ability to generalize.
2 min read
Robot being trained using a virtual reality interface
Reinforcement Learning

A Robot in Every Kitchen

Every home is different. That makes it difficult for domestic robots to translate skills learned in one household into another. Training in virtual reality, where the robot has access to rich information about three-dimensional objects, can make it easier to generalize skills to the real world.
2 min read
Simulated hide-and-seek environment
Reinforcement Learning

Ready or Not

Independent research lab OpenAI designed virtual agents to play hide-and-seek. They evolved increasingly clever strategies, eventually hacking the game world’s physics to gain advantage.
2 min read
Continuous Planner for One-Shot Imitation Learning
Reinforcement Learning

Working Through Uncertainty

How to build robots that respond to novel situations? When prior experience is limited, enabling a model to describe its uncertainty can enable it to explore more avenues to success.
2 min read
Arcade game
Reinforcement Learning

Leveling the Playing Field

Deep reinforcement learning has given machines apparent hegemony in vintage Atari games, but their scores have been hard to compare — with one another or with human performance — because there are no rules governing what machines can and can’t do to win. Researchers aim to change that.
2 min read
Google Research Football video
Reinforcement Learning

Get Your Kicks With DRL

Researchers typically test deep reinforcement learning algorithms on games from Space Invaders to StarCraft. The Google Brain team in Zurich adds another option: football, also known as soccer.
2 min read
GO match: AlphaGo vs. Lee Sedol
Reinforcement Learning

DeepMind Results Raise Questions

Alphabet subsidiary DeepMind lost $572 million in the past year, and its losses over the last three years amounted to more than $1 billion. AI contrarian Gary Marcus used the news as an opportunity to question the direction of AI as an industry.
2 min read

Subscribe to The Batch

Stay updated with weekly AI News and Insights delivered to your inbox