Deep reinforcement learning has recently shown many impressive successes. However, one major obstacle towards applying such methods to real-world problems is their lack of data-efficiency. To this end, we propose the Bottleneck Simulator: a model-based reinforcement learning method which combines a learned, factorized transition model of the environment with rollout simulations to learn an effective policy from few examples. The learned transition model employs an abstract, discrete (bottleneck) state, which increases sample efficiency by reducing the number of model parameters and by exploiting structural properties of the environment. We provide a mathematical analysis of the Bottleneck Simulator in terms of fixed points of the learned policy, which reveals how performance is affected by four distinct sources of error: an error related to the abstract space structure, an error related to the transition model estimation variance, an error related to the transition model estimation bias, and an error related to the transition model class bias. Finally, we evaluate the Bottleneck Simulator on two natural language processing tasks: a text adventure game and a real-world, complex dialogue response selection task. On both tasks, the Bottleneck Simulator yields excellent performance beating competing approaches.
Golfers around the world all have one thing in common: They despise rain. The weather can really put a damper on a round of golf, especially when you've waited all winter to get back out on the course. That's where the PhiGolf home golf simulator can save the day. Successfully funded on Indiegogo with over $200,000, the PhiGolf simulator and swing stick allow you to play golf all year round, no matter the weather, from practically anywhere. It's kind of like a video game, except the swing stick trainer is your controller.
We present a framework for automatically structuring and training fast, approximate, deep neural surrogates of existing stochastic simulators. Unlike traditional approaches to surrogate modeling, our surrogates retain the interpretable structure of the reference simulators. The particular way we achieve this allows us to replace the reference simulator with the surrogate when undertaking amortized inference in the probabilistic programming sense. The fidelity and speed of our surrogates allow for not only faster "forward" stochastic simulation but also for accurate and substantially faster inference. We support these claims via experiments that involve a commercial composite-materials curing simulator. Employing our surrogate modeling technique makes inference an order of magnitude faster, opening up the possibility of doing simulator-based, non-invasive, just-in-time parts quality testing; in this case inferring safety-critical latent internal temperature profiles of composite materials undergoing curing from surface temperature profile measurements.
That might not sound like much, but in the quantum computing arms race, several groups are edging past one another as they aim to eventually make a universal quantum computer. A group of researchers at the Joint Quantum Institute has created a quantum simulator using 53 quantum bits, or qubits. Earlier this month, IBM announced a 50-qubit prototype, though its capabilities are unclear. With this 53-qubit device, the researchers have done scientific simulations that don't seem to be possible
Hang onto your straw hats, folks, Farming Simulator is getting its own esports league. After testing the water with the Farming Simulator Championships in 2018, the folks at Giants Software announced the Farming Simulator League for 2019, a new esports league that pits teams of Farming Simulator players against each other in farm-related activities for huge cash prizes. SEE ALSO: We hired a game tutor to get better at Fortnite. If you don't know what Farming Simulator is, it's a video game series where players simulate the day-to-day activities of operating a modern farm, which involves a whole lot of driving realistic tractors back and forth across fields. It may not sound like much to people who haven't played it, but the series is wildly popular in Europe and has been picking up steam in other areas of the world in recent years.