Inverse reinforcement learning (IRL) aims to infer a reward from expert demonstrations, motivated by the idea that the reward, rather than the policy, is the most succinct and transferable description of a task [Ng et al., 2000]. However, the reward corresponding to an optimal policy is not unique, making it unclear if an IRL-learned reward is transferable to new transition laws in the sense that its optimal policy aligns with the optimal policy corresponding to the expert's true reward. Past work has addressed this problem only under the assumption of full access to the expert's policy, guaranteeing transferability when learning from two experts with the same reward but different transition laws that satisfy a specific rank condition [Rolland et al., 2022]. In this work, we show that the conditions developed under full access to the expert's policy cannot guarantee transferability in the more practical scenario where we have access only to demonstrations of the expert. Instead of a binary rank condition, we propose principal angles as a more refined measure of similarity and dissimilarity between transition laws. Based on this, we then establish two key results: 1) a sufficient condition for transferability to any transition laws when learning from at least two experts with sufficiently different transition laws, and 2) a sufficient condition for transferability to local changes in the transition law when learning from a single expert. Furthermore, we also provide a probably approximately correct (PAC) algorithm and an end-to-end analysis for learning transferable rewards from demonstrations of multiple experts.

Inverse reinforcement learning (IRL) aims to infer a reward from expert demonstrations, motivated by the idea that the reward, rather than the policy, is the most succinct and transferable description of a task [Ng et al., 2000]. However, the reward corresponding to an optimal policy is not unique, making it unclear if an IRL-learned reward is transferable to new transition laws in the sense that its optimal policy aligns with the optimal policy corresponding to the expert's true reward. Past work has addressed this problem only under the assumption of full access to the expert's policy, guaranteeing transferability when learning from two experts with the same reward but different transition laws that satisfy a specific rank condition [Rolland et al., 2022]. In this work, we show that the conditions developed under full access to the expert's policy cannot guarantee transferability in the more practical scenario where we have access only to demonstrations of the expert. Instead of a binary rank condition, we propose principal angles as a more refined measure of similarity and dissimilarity between transition laws.

Recent advancements in natural language generation (NLG) technology have significantly improved the diversity, control, and quality of large language models (LLM)-generated text. A notable example is OpenAI's ChatGPT, which demonstrates exceptional performance in tasks such as answering questions, composing email messages, essays, and codes. However, this newfound capability to produce human-like text at high efficiency also raises concerns about detecting and preventing misuse of LLMs in tasks such as phishing, disinformation, and academic dishonesty. For instance, many schools banned ChatGPT due to concerns over cheating in assignments,11 and media outlets have raised the alarm over fake news generated by LLMs.14 These concerns about the misuse of LLMs have hindered the NLG application in important domains such as media and education.

Motivated by the power of machine-learned predictions, the field of learningaugmented algorithms has been growing rapidly in recent years. In the classical field of online algorithms, an input sequence is revealed to an algorithm over time and it is assumed that at all times, no information about the future part of the input is available. In contrast, a learning-augmented algorithm additionally has access to predictions (e.g., machine-learned) related to the future input. These predictions may be inaccurate, so a challenge is to simultaneously utilize high-quality predictions to their best advantage while at the same time avoiding to be misled by erroneous predictions. An important technique in the field of learning-augmented algorithms is the method of combining multiple algorithms into a single hybrid algorithm that leverages the advantages of all individual algorithms. The basic idea goes back to several decades before the area of learning-augmented algorithms was born and also has applications, for example, in pure online algorithms: Fiat et al. [1990] defined a MIN operator on algorithms for the k-server problem that combines several algorithms into one whose cost matches the best of them up to

Twitter CEO Elon Musk opens up how about his takeover of the company and his mission to ensure free speech on'Tucker Carlson Tonight.' Billionaire tech mogul Elon Musk revealed in an exclusive interview with Fox News' Tucker Carlson that the United States, along with foreign government agencies, was granted "full access" to direct messages of private citizens on Twitter prior to his takeover. Musk made the bombshell allegation in the Carlson sit-down, the first part of which aired Monday on "Tucker Carlson Tonight." In a rare and unfiltered discussion, the Tesla and SpaceX CEO spoke candidly about his concerns about artificial intelligence (AI), his Twitter acquisition and his future plans for the social media platform that he bought last fall. In what has been described as one of the most "jaw-dropping" moments of the two-part conversation, Musk accused his predecessors at Twitter of allowing U.S. and foreign intelligence agencies to read users' direct messages on the platform, calling it among the most "absurd" discoveries he made since purchasing the company for $44 billion. MUSK BLASTS BBC REPORTER WHO CLAIMS TWITTER HAS RISE IN HATE SPEECH: 'YOU CAN'T NAME A SINGLE EXAMPLE' "The degree to which government agencies effectively had full access to everything that was going on on Twitter blew my mind," Musk told Carlson.

Clearly, we need to do something about how we talk about open source and openness in general. It's been clear since at least 2006 when I rightly got smacked down for calling out Google and Yahoo! for holding back on open source. As Tim O'Reilly wrote at the time, in a cloud era of open source, "one of the motivations to share--the necessity of giving a copy of the source in order to let someone run your program--is truly gone." In fact, he went on, "Not only is it no longer required, in the case of the largest applications, it's no longer possible." That impossibility of sharing has roiled the definition of open source during the past decade, and it's now affecting the way we think about artificial intelligence (AI), as Mike Loukides recently noted.

What is the impact of artificial intelligence (AI) and big data on societies in the Indo-Pacific? How are countries using AI and big data to enhance their national security and advance their national interests? And what are the major regulatory issues? For a perspective on these and other matters, Jongsoo Lee interviewed Simon Chesterman, dean and provost's chair professor of the National University of Singapore Faculty of Law and senior director of AI Governance at AI Singapore. What are nations in the Indo-Pacific doing to develop their artificial intelligence (AI) and big data capabilities?

Earlier this year, a Chinese technology executive published an opinion piece arguing that size is China's greatest asset in technology competition with the United States today. His argument was simple: Innovation in emerging technologies such as artificial intelligence is partly a function of absolute numbers of scientists and engineers, and, as China continues to expand its domestic talent pipeline, its strength in numbers will soon far exceed that of the United States. Many in Washington seem to agree. The White House's education strategy draws motivation from China's rapidly increasing number of university graduates. Experts lament the United States' dependence on international talent and draw analogies with Sputnik to call for crisis-level educational spending levels similar to those in the post-Sputnik era.

With the presence of artificial intelligence (AI) everywhere and the increased use of deep learning (DL), many security practitioners are being hooked into believing that these approaches are the solution for the security challenges. Nevertheless, like any tool, AI is a double-edged sword that can be used as a security solution or as a weapon by hackers. In fact, many security researchers and industry have told AI will be the biggest ally of security. Moreover, we can see that by the increased number of companies that merging AI and Cybersecurity to keep us safe. But has anyone ever thought that these same techniques can be applied to improve the tools and methods used by hackers?

The U.S. government, long a proponent of advancing technology for military purposes, sees artificial intelligence as key to the next generation of fighting tools. Several recent investments and Pentagon initiatives show that military leaders are concerned about keeping up with – and ahead of – China and Russia, two countries that have made big gains in developing artificial-intelligence systems. AI-powered weapons include target recognition systems, weapons guided by AI, and cyberattack and cyberdefense software that runs without human intervention. The U.S. defense community is coming to understand that AI will significantly transform, if not completely reinvent, the world's military power balance. The concern is more than military.