Recently, Model-based Reinforcement Learning (MBRL) methods have demonstrated stunning sample efficiency in various RL domains.However, achieving this extraordinary sample efficiency comes with additional training costs in terms of computations, memory, and training time.To address these challenges, we propose the Pa

Recently, Model-based Reinforcement Learning (MBRL) methods have demonstrated stunning sample efficiency in various RL domains.However, achieving this extraordinary sample efficiency comes with additional training costs in terms of computations, memory, and training time.To address these challenges, we propose the Parallelized Model-based Reinforcement Learning (PaMoRL) framework.PaMoRL introduces two novel techniques: the Parallel World Model (PWM) and the Parallelized Eligibility Trace Estimation (PETE) to parallelize both model learning and policy learning stages of current MBRL methods over the sequence length.Our PaMoRL framework is hardware-efficient and stable, and it can be applied to various tasks with discrete or continuous action spaces using a single set of hyperparameters.The empirical results demonstrate that the PWM and PETE within PaMoRL significantly increase training speed without sacrificing inference efficiency.In terms of sample efficiency, PaMoRL maintains an MBRL-level sample efficiency that outperforms other no-look-ahead MBRL methods and model-free RL methods, and it even exceeds the performance of planning-based MBRL methods and methods with larger networks in certain tasks.

Resident Moz search scientist Dr. Pete Meyers returns to the MozCon stage this year, and we're so excited for his presentation: Rule Your Rivals: From Data to Action. In our last interview before the show, we talked with Dr. Pete about 2020, the trends he's seeing in the SERPs, and what makes competitive analysis effective. Read the full interview below, and don't forget to grab your ticket to see Dr. Pete and our other amazing speakers at MozCon Virtual 2021 (ticket sales end Friday, July 9!): Question: 2020 was quite a year, how was this year for you? Did you have any favorite projects? Dr. Pete: Honestly, there were a lot of days this past year when it felt like just staying alive and sane were our main project (and I'm not sure I completed the sane part).

Semantic web technologies have shown their effectiveness, especially when it comes to knowledge representation, reasoning, and data integrations. However, the original semantic web vision, whereby machine readable web data could be automatically actioned upon by intelligent software web agents, has yet to be realised. In order to better understand the existing technological challenges and opportunities, in this paper we examine the status quo in terms of intelligent software web agents, guided by research with respect to requirements and architectural components, coming from that agents community. We start by collating and summarising requirements and core architectural components relating to intelligent software agent. Following on from this, we use the identified requirements to both further elaborate on the semantic web agent motivating use case scenario, and to summarise different perspectives on the requirements when it comes to semantic web agent literature. Finally, we propose a hybrid semantic web agent architecture, discuss the role played by existing semantic web standards, and point to existing work in the broader semantic web community any beyond that could help us to make the semantic web agent vision a reality.

Ten years ago, the most forward-thinking companies were just starting to dive into the potential of data and analytics. Since then, brands have moved from using analytics to answer what customers are doing to exploring the how and why, and also to figure out what they will do in the future. The Wharton Customer Analytics Initiative (WCAI) is celebrating its 10th anniversary this year and has seen every step of that evolution. Knowledge@Wharton recently sat down with Wharton marketing professors Eric Bradlow, Peter Fader and Raghuram Iyengar to discuss how the field has developed over time, and what they expect to be the key trends over the next decade. Bradlow and Fader are the founding directors of WCAI, and Bradlow and Iyengar are the current co-directors. An edited transcript of the conversation follows. Knowledge@Wharton: When WCAI launched ten years ago, what was the environment like in the field of analytics? What were some of the initiative's key goals? Peter Fader: Even though the initiative started 10 years ago, the idea started about a decade before that.

If I see a robot coming to kill me, I'll just look for the off-switch or how I can unplug it". I'm ever so slightly paraphrasing Pete Trainor, one of yesterday's speakers at Wired Health 2018, but this was the jist of what he said to me over a coffee as we discussed AI, robotics and its place in the the world. And if I can draw a theme from yesterday's excellent Wired Health event held at the very impressive Francis Crick Institute, it's that AI, robotics and digital technology are not here to replace people in healthcare provision. Rather, they are here to augment and "scale-up" the amount that a healthcare professional can do. This was a theme which was alighted on by a number of speakers.

Several years ago, Canary Pete's political cartoon flooded email inboxes and social media pages. The humorous illustration showed a middle-aged executive walking into a typical job interview, with the exception that he had to build his own office chair (since he was applying to work at IKEA). Pete's satire might be short-lived, as last week the robotics industry achieved a new milestone – building an IKEA chair in less than 10 minutes! It is unclear how soon bots will be replacing human assemblers like TaskRabbit, but in the the words of Jackie DeChamps, Chief Operating Officer of IKEA USA,"We are always looking at ways we can innovate and help make our customers' lives at home easier." Addressing the elephant in the room, I debated a colleague earlier this month at The Frontier Conference in New Orleans. I expressed that it is critical for mechatronic companies to engage early with organized labor for successful deployments.

I had the opportunity to glimpse a large part of the future this week. I think you will find it as amazing as I did. Dr. Kiron Skinner, a remarkable scholar, hosted me at Carnegie Mellon University in Pittsburgh. According to the U.S. News & World Report's "Best Colleges" rankings, Carnegie Mellon has the nation's top graduate level artificial intelligence (AI) program and one of the top five undergraduate computer engineering programs. On Wednesday, the people at Carnegie Mellon showed me a few of the reasons they are held in such high regard.

"The reason no other animals evolved like humans, is they watched what we did. Then instead of doing that, they concentrated on the important things, like their basic needs and expanding their minds, to eventually speak telepathically, all the while unbeknown to us. It was quite brilliant in its subtlety." That's not from the story which follows, but it's a good introduction and from another one I'm writing. Like that, this is about animal sentience. So I imagined the young character from my children's book, with her talking dog and cat.

This room of the university's Artificial Intelligence Lab looked like the study of an Oxford don. The walls were covered with bookcases and -- of course! There was a small end-table with a lace doily. The visitors were not at all what one might expect in a computer lab. There was a Catholic priest, a Lutheran minister and a rabbi.