We develop a framework for interacting with uncertain environments in reinforcement learning (RL) by leveraging preferences in the form of utility functions. We claim that there is value in considering different risk measures during learning. In this framework, the preference for risk can be tuned by variation of the parameter $\beta$ and the resulting behavior can be risk-averse, risk-neutral or risk-taking depending on the parameter choice. We evaluate our framework for learning problems with model uncertainty. We measure and control for \emph{epistemic} risk using dynamic programming (DP) and policy gradient-based algorithms. The risk-averse behavior is then compared with the behavior of the optimal risk-neutral policy in environments with epistemic risk.

According to the Software and Information Industry Association (SIIA), the CODiE Awards have honored thousands of software, education, information and media products for achieving excellence and innovation in technology for over 30 years. "They are the only peer-recognized program in the business and education technology industries, so each CODiE Award win serves as incredible market validation for a product's innovation, vision, and overall industry impact. The CODiE Awards highlights the very best products, innovators and leaders in today's tech market." Separately, the Adobe XD Team was also honored in the "Product Team of the Year" category, as well as Adobe Captivate Prime for "Best Corporate / Enterprise Learning Solution." Adobe Sensei was recognized in the "Best Artificial Intelligence Enabled Solution" category as the "solution best able to augment human intelligence and better automate decision support tasks" by incorporating "machine and deep learning algorithms into its everyday functionality."

This UC Berkeley School of Information online short course is delivered in collaboration with GetSmarter. Learn from industry thought leaders as you gain the skills needed to develop an AI strategy, and lead the transformation in your organization. The design of this online course is guided by UC Berkeley School of Information faculty and industry experts who will share their experience and in-depth subject knowledge with you throughout the course.

I am often asked about artificial intelligence and the future of work. My answer is that A.I. will change 100% of current jobs. It will change the job of a factory worker. It will change the job of a software developer, of a customer service agent, of a professional driver. And it will change my job as the CEO of one of the biggest technology companies in the world.

The autonomous vehicle industry is looking a lot like a middle-school dance. Monday, Aurora and Fiat Chrysler Automobiles announced they would work together to put the startup's self-driving tech, called Aurora Driver, into FCA's commercial vehicles, including cargo vans and Ram pickup trucks. On Tuesday, word leaked that Aurora and Volkswagen had discontinued their 18-month joint effort to build an urban robotaxi system. Wednesday, Aurora and Hyundai said they're doubling down on their own partnership, with the South Korean company (and its conglomerate partner, Kia) pouring more money into Aurora's now $600 million Series B financing round. The companies will continue to work together to build Aurora's tech into Hyundai's hydrogen-powered Nexo.

The government has announced an investment of up to £18.5m to support efforts to enhance diversity in artificial intelligence (AI) and data science roles. Part of a wider plan to upskill the UK workforce as part of the AI Sector Deal to position the country as a leader in use of the technology, £13.5m of the total funding will go towards up to 2,500 AI and data science conversion courses for professionals who have degrees in other disciplines, as well as 1,000 scholarships. The programmes will aim to support applications from professionals returning from a career break and looking to retrain, as well as under-represented groups in the digital workforce, including women and those from minority ethnic or lower socio-economic backgrounds. Around £5m will be invested into the Adult Learning Technology Innovation Fund, to be launched in partnership with innovation foundation Nesta, which will seek to encourage companies to use AI and automation to improve online learning platforms aimed at helping adults retrain. "The UK has a long-standing reputation for innovation, world-leading academic institutions and a business-friendly environment. Everyone, regardless of their background, should have the opportunity to build a successful career in our world-leading tech sector," said digital secretary Jeremy Wright.

Artificial Intelligence (AI) is transforming the food industry by opening the doors to innovation and new product development (NPD), aligning to global food trends. This is not only limited to developed economies but is also taking off in emerging economies. A new Brazilian start-up company, Fazenda Futuro has developed a vegan burger using AI technology. The burger has the taste, smell and texture uncannily like the regular meat version, and is prepared from ingredients that include pea, soy, and chickpea protein. The'Futuro' burger also has the same nutritional value as a regular beef burger.

Machine Learning, often abbreviated to ML, is a form of learning in which systems use complex computer algorithms to acquire knowledge or skill automatically without being programmed directly. It is considered as a type of AI (Artificial Intelligence) since machines are built with the idea to learn and make decisions from the available data and even improve themselves from experience without requiring human involvement. This is mainly used to maximize the machine's performance. The idea behind ML is based on mathematics, computer science, and statistics. Additionally, great scientists such as Andrey Markov, Thomas Bayes, and Carl Friedrich Gauss have contributed in the invention of statistical models like Markov Chains, Bayes Theorem, and the method of Least-Square respectively which are used a great deal in the Machine Learning algorithms.

Hierarchical Reinforcement Learning is a promising approach to long-horizon decision-making problems with sparse rewards. Unfortunately, most methods still decouple the lower-level skill acquisition process and the training of a higher level that controls the skills in a new task. Treating the skills as fixed can lead to significant sub-optimality in the transfer setting. In this work, we propose a novel algorithm to discover a set of skills, and continuously adapt them along with the higher level even when training on a new task. Our main contributions are two-fold. First, we derive a new hierarchical policy gradient, as well as an unbiased latent-dependent baseline. We introduce Hierarchical Proximal Policy Optimization (HiPPO), an on-policy method to efficiently train all levels of the hierarchy simultaneously. Second, we propose a method of training time-abstractions that improves the robustness of the obtained skills to environment changes. Code and results are available at sites.google.com/view/hippo-rl .

This paper aims at learning representations for long sequences of continuous signals. Recently, the BERT model has demonstrated the effectiveness of stacked transformers for representing sequences of discrete signals (i.e. word tokens). Inspired by its success, we adopt the stacked transformer architecture, but generalize its training objective to maximize the mutual information between the masked signals, and the bidirectional context, via contrastive loss. This enables the model to handle continuous signals, such as visual features. We further consider the case when there are multiple sequences that are semantically aligned at the sequence-level but not at the element-level (e.g. video and ASR), where we propose to use a Transformer to estimate the mutual information between the two sequences, which is again maximized via contrastive loss. We demonstrate the effectiveness of the learned representations on modeling long video sequences for action anticipation and video captioning. The results show that our method, referred to by Contrastive Bidirectional Transformer ({\bf CBT}), outperforms various baselines significantly. Furthermore, we improve over the state of the art.