Despite a series of recent successes in reinforcement learning (RL), many RL algorithms remain sensitive to hyperparameters. As such, there has recently been interest in the field of AutoRL, which seeks to automate design decisions to create more general algorithms. Recent work suggests that population based approaches may be effective AutoRL algorithms, by learning hyperparameter schedules on the fly. In particular, the PB2 algorithm is able to achieve strong performance in RL tasks by formulating online hyperparameter optimization as time varying GP-bandit problem, while also providing theoretical guarantees. However, PB2 is only designed to work for \emph{continuous} hyperparameters, which severely limits its utility in practice. In this paper we introduce a new (provably) efficient hierarchical approach for optimizing \emph{both continuous and categorical} variables, using a new time-varying bandit algorithm specifically designed for the population based training regime. We evaluate our approach on the challenging Procgen benchmark, where we show that explicitly modelling dependence between data augmentation and other hyperparameters improves generalization.

RaceVLA presents an innovative approach for autonomous racing drone navigation by leveraging Visual-Language-Action (VLA) to emulate human-like behavior. This research explores the integration of advanced algorithms that enable drones to adapt their navigation strategies based on real-time environmental feedback, mimicking the decision-making processes of human pilots. The model, fine-tuned on a collected racing drone dataset, demonstrates strong generalization despite the complexity of drone racing environments. RaceVLA outperforms OpenVLA in motion (75.0 vs 60.0) and semantic generalization (45.5 vs 36.3), benefiting from the dynamic camera and simplified motion tasks. However, visual (79.6 vs 87.0) and physical (50.0 vs 76.7) generalization were slightly reduced due to the challenges of maneuvering in dynamic environments with varying object sizes. RaceVLA also outperforms RT-2 across all axes - visual (79.6 vs 52.0), motion (75.0 vs 55.0), physical (50.0 vs 26.7), and semantic (45.5 vs 38.8), demonstrating its robustness for real-time adjustments in complex environments. Experiments revealed an average velocity of 1.04 m/s, with a maximum speed of 2.02 m/s, and consistent maneuverability, demonstrating RaceVLA's ability to handle high-speed scenarios effectively. These findings highlight the potential of RaceVLA for high-performance navigation in competitive racing contexts. The RaceVLA codebase, pretrained weights, and dataset are available at this http URL: https://racevla.github.io/

People Can Fly is one of the leading independent AAA games development studios with an international team of hundreds of talented individuals working from offices located in Poland, UK, US, and Canada, and from all over the world thanks to our remote work programs. Founded in 2002, we made our mark on the shooter genre with titles such as Painkiller, Bulletstorm, Gears of War: Judgment, and Outriders. We are one of the most experienced Unreal Engine studios in the industry and we are expanding it with in-house solutions called PCF Framework. Our creative teams are currently working on several exciting titles: Gemini is our new project being developed with Square Enix; Bifrost, Victoria and Dagger are projects we're growing in the self-publishing model. We also have one project in the concept phase – Red; as well as two projects in VR technology – Green Hell VR and Thunder - a new project based on one of the IPs from the Group's portfolio.

People Can Fly is one of the leading independent AAA games development studios with an international team of hundreds of talented individuals working from offices located in Poland, UK, US, and Canada, and from all over the world thanks to our remote work programs. Founded in 2002, we made our mark on the shooter genre with titles such as Painkiller, Bulletstorm, Gears of War: Judgment, and Outriders. We are one of the most experienced Unreal Engine studios in the industry and we are expanding it with in-house solutions called PCF Framework. Our creative teams are currently working on several exciting titles: Gemini is our new project being developed with Square Enix; Bifrost, Victoria and Dagger are projects we're growing in the self-publishing model. We also have one project in the concept phase – Red; as well as two projects in VR technology – Green Hell VR and Thunder - a new project based on one of the IPs from the Group's portfolio.

Founded in 2012, Incuvo is a studio of nearly 50 individuals working from Poland, Katowice. We have established our position worldwide in the VR games area, developing such titles like Layers of Fear VR and Blair Witch VR. With 10 years of experience in making games and being engaged in the VR technology since 2019, Incuvo is aiming to expand the genre even further and become one of the key developers of the growing VR market worldwide. We want to combine our expertise with the creativity and skills of ambitious professionals to work on the new generation of VR titles. Our team is working currently on Green Hell VR and the VR version of the game from PCF Group's portfolio.

People Can Fly is one of the leading independent AAA games development studios with an international team of hundreds of talented individuals working from offices located in Poland, UK, US, and Canada, and from all over the world thanks to our remote work programs. Founded in 2002, we made our mark on the shooter genre with titles such as Painkiller, Bulletstorm, Gears of War: Judgment, and Outriders. We are one of the most experienced Unreal Engine studios in the industry and we are expanding it with in-house solutions called PCF Framework. Our creative teams are currently working on several exciting titles: Gemini is our new project being developed with Square Enix; Bifrost, Victoria and Dagger are projects we're growing in the self-publishing model. We also have one project in the concept phase – Red; as well as two projects in VR technology – Green Hell VR and Thunder - a new project based on one of the IPs from the Group's portfolio.

Originally published on Towards AI the World's Leading AI and Technology News and Media Company. If you are building an AI-related product or service, we invite you to consider becoming an AI sponsor. At Towards AI, we help scale AI and technology startups. Let us help you unleash your technology to the masses. Generate infinite new frames as if you would be flying into your image!

Google has created a program where the viewer can "fly into" a still photo using artificially intelligent (AI) 3D models. In a new paper entitled InfiniteNature-Zero, the researchers take a landscape photo and then use AI to "fly" into it like a bird, with clever software generating a fake landscape thanks to machine learning. When facing the daunting task, researchers had to fill in information that a still photo doesn't provide, such as hidden areas in a photo. For example, a spot that is hidden behind trees needs to be generated. This can be done by "inpainting," the AI will simulate what it thinks would be there by the process of machine learning with huge datasets.

There will never be the perfect drone for everyone. There are too many different reasons for owning a drone. Some like to shoot sweeping cinematic masterpieces, and some want to follow fast-paced action. What makes a drone good at one thing often makes it not so great for another. That said, if you're after speed and maneuverability, the Skydio 2 is darn near perfect. It does have some shortcomings, which I'll get to below.

Planning--the ability to synthesize a course of action to achieve desired goals--is an important part of intelligent agency and has thus received significant attention within AI for more than 30 years. Work on efficient planning algorithms still continues to be a hot topic for research in AI and has led to several exciting developments in the past few years. This article provides a tutorial introduction to all the algorithms and approaches to the planning problem in AI. To fulfill this ambitious objective, I introduce a generalized approach to plan synthesis called refinement planning and show that in its various guises, refinement planning subsumes most of the algorithms that have been, or are being, developed. It is hoped that this unifying overview provides the reader with a brand-name-free appreciation of the essential issues in planning.