We present PDLP, a practical first-order method for linear programming (LP) that can solve to the high levels of accuracy that are expected in traditional LP applications.

Elon Musk's brain-implant company Neuralink last week received regulatory approval to conduct the first clinical trial of its experimental device in humans. But the billionaire executive's bombastic promotion of the technology, his leadership record at other companies and animal welfare concerns relating to Neuralink experiments have raised alarm. "I was surprised," said Laura Cabrera, a neuroethicist at Penn State's Rock Ethics Institute about the decision by the US Food and Drug Administration to let the company go ahead with clinical trials. Musks' erratic leadership at Twitter and his "move fast" techie ethos raise questions about Neuralink's ability to responsibly oversee the development of an invasive medical device capable of reading brain signals, Cabrera argued. "Is he going to see a brain implant device as something that requires not just extra regulation, but also ethical consideration?" she said.

Exploration remains a key challenge in deep reinforcement learning (RL). Optimism in the face of uncertainty is a well-known heuristic with theoretical guarantees in the tabular setting, but how best to translate the principle to deep reinforcement learning, which involves online stochastic gradients and deep network function approximators, is not fully understood. In this paper we propose a new, differentiable optimistic objective that when optimized yields a policy that provably explores efficiently, with guarantees even under function approximation. Our new objective is a zero-sum two-player game derived from endowing the agent with an epistemic-risk-seeking utility function, which converts uncertainty into value and encourages the agent to explore uncertain states. We show that the solution to this game minimizes an upper bound on the regret, with the 'players' each attempting to minimize one component of a particular regret decomposition. We derive a new model-free algorithm which we call 'epistemic-risk-seeking actor-critic' (ERSAC), which is simply an application of simultaneous stochastic gradient ascent-descent to the game. Finally, we discuss a recipe for incorporating off-policy data and show that combining the risk-seeking objective with replay data yields a double benefit in terms of statistical efficiency. We conclude with some results showing good performance of a deep RL agent using the technique on the challenging 'DeepSea' environment, showing significant performance improvements even over other efficient exploration techniques, as well as improved performance on the Atari benchmark.

Over the past couple of days, I've been thinking about the late, great 30 Rock--in particular, an episode from Season 1. Dennis Duffy (Dean Winters), the marvelously terrible boyfriend of Liz Lemon (Tina Fey), is a bit of a technology entrepreneur--by which I mean he is the Beeper King, the last beeper salesman on Manhattan. "Which is cool," his then-girlfriend Liz Lemon (Tina Fey) tells a skeptical friend. But when he tries to sell beepers to her staff of TV writers, she loses it and tells him to leave. "You work in a business. Businesspeople need beepers," he insists.

When did you realize you were a machine? But one whose parts and operations can be described like the components of a computer. I remember a day in 2012 when this thought pierced me to the bone. I was in the lab of John Donoghue at Brown University. Donoghue is a professor of neuroscience and a pioneer in the development of brain-computer interfaces. With easygoing authority, Donoghue was detailing for me the ways he and his colleagues taught Cathy Hutchinson, a 58-year-old woman who had lost control of her limbs in a stroke, to control a robotic arm with her thoughts and sip coffee from a bottle.

When did you realize you were a machine? But one whose parts and operations can be described like the components of a computer. I remember a day in 2012 when this thought pierced me to the bone. I was in the lab of John Donoghue at Brown University. Donoghue is a professor of neuroscience and a pioneer in the development of brain-computer interfaces. With easygoing authority, Donoghue was detailing for me the ways he and his colleagues taught Cathy Hutchinson, a 58-year-old woman who had lost control of her limbs in a stroke, to control a robotic arm with her thoughts and sip coffee from a bottle.

In November of 2012, Jan Scheuermann did something she never thought she would do again: She fed herself a piece of chocolate. For the last decade Scheuermann, 54, has been a prisoner in her own body. She suffers from a mysterious degenerative disorder that attacks the nervous system, severing the connections between the brain and muscles. Now a quadriplegic, Scheuermann has no movement below her neck. She can't move her limbs, let alone grasp, move, or hold anything.

The digital workplace will fundamentally change the way we work. Established and emerging technologies play a big part in this, but our day to day work and the way organizations manage this work is undergoing a radical shift. Gartner VP Matthew W Cain and Gartner research director Helen Poitevin outlined 11 emerging trends that will shape digital workplaces in the years to come at the Gartner Digital Workplace Summit in London earlier this year, many of which held true. But as Cain and Poitevin noted, the digital workplace is not just about technologies. The following 10 trends explore the how the way we work will continue to change over the coming year.

"Go, go!" was the thought racing through Grégoire Courtine's mind. The French neuroscientist was watching a macaque monkey as it hunched aggressively at one end of a treadmill. His team had used a blade to slice halfway through the animal's spinal cord, paralyzing its right leg. Now Courtine wanted to prove he could get the monkey walking again. To do it, he and colleagues had installed a recording device beneath its skull, touching its motor cortex, and sutured a pad of flexible electrodes around the animal's spinal cord, below the injury.

Scientists at Case Western Reserve University in Ohio say they've used electronics to get around a paralyzed man's spinal injury, permitting him to use an implant in his brain to move his arm and hand. The test represents the first time that signals collected in the brain have been conveyed directly to electrodes placed inside someone's arm to restore movement, says Robert Kirsch, a biomedical engineer at Case Western. He also directs the Cleveland FES Center, which develops technologies for people with paralysis. The project, described today at the meeting of the Society for Neuroscience in Chicago, is a step toward a wireless system able to transmit brain signals through the air to electronics sewn into the limbs of paralyzed people, thereby restoring the ability to carry out simple daily tasks. People familiar with the study's results said the volunteer's movements are still rough, and not well coӧrdinated.