Watcher Entertainment is an American digital media and entertainment company, founded by Steven Lim, Shane Madej, and Ryan Bergara. The channel features a variety of comedy, paranormal, gaming, cooking, and educational shows – typically hosted by Madej and Bergara. The Watcher main channel has over 400 million views and 2.9 million subscribers. The company launched their own streaming service, WatcherTV, in 2024. == History == === Buzzfeed and the creation of Watcher Entertainment (2019) === Madej, Bergara, and Lim met while working at the digital media company BuzzFeed. Madej and Bergara were co-hosts of the popular true crime and paranormal series Buzzfeed Unsolved and Lim was the creator and co-host of the popular internet food series Worth It. Both shows generated a combined 2 billion views with 15 billion minutes watched, making them two of the most successful shows on Buzzfeed. In 2019, Madej, Bergara, and Lim quit Buzzfeed as full-time employees. They each stayed on as contracted employees to complete their respective shows. The trio credited their departure to their desire to found a company with more "creative opportunities" and the ability to have "actual ownership of the content" made. The company is majority-owned by the trio. They received funding from Neuro, a caffeinated energy gum company; Boba Guys, a bubble-milk tea chain; and Steve Chen, a YouTube co-founder. Watcher Entertainment gained its name from the infamous true crime case of The Westfield Watcher, which Madej and Bergara had covered in a Buzzfeed Unsolved episode. The trio began the company as co-CEOs; however, Bergara and Madej stepped down from the role in 2023 to focus on content creation. === Watcher Entertainment (2020–present) === Watcher Entertainment was launched in January 2020. The company debuted with seven series and a weekly interactive talk show: Homemade, Grocery Run, Weird Wonderful World, Puppet History, Tourist Trapped, Top 5 Beatdown, Spooky Small Talk, and Watcher Weekly. The channel reached over 300,000 subscribers within the first month of launching. They were signed by talent agency CAA in the same year. Puppet History, a comedy educational game show, quickly became a success and gained a significant audience. The show, which stars Madej as a fluffy blue puppet, has spanned seven seasons and led to the creation of a variety of merchandise. It has featured a variety of guest stars on every episode, including other former Buzzfeed employees. The company premiered its first horror series in July 2020 with Are You Scared?. Following the end of Buzzfeed Unsolved: Supernatural in 2021, the studio premiered its highly anticipated successor, Ghost Files, just months after. The show followed a similar format, with Bergara and Madej investigating reportedly haunted locations and attempting to find evidence of the paranormal. The show had significant success, with critics noting the improved production value and design from its predecessor. In 2023, Bergara and Madej went on a tour across the United States to premiere episodes of the second season. The series was renewed for a third season, which they premiered with a United Kingdom tour in 2024. That year, Watcher premiered a light-hearted successor to the graphic Buzzfeed Unsolved: True Crime, with Mystery Files. In this rendition, Bergara or Madej present unusual crime or supernatural mysteries with a collection of theoretical solutions. The show was met with great success by audiences and was quickly renewed for a second season. Watcher launched a second channel, 'WatcherPodcasts,' in October 2023. The channel features podcasts hosted by Lim, Bergara, and Madej. On April 19, 2024, the company launched its Watcher streaming service. Going forward, all of their content would be released exclusively on the service and the company planned to transition away from YouTube. This announcement was met with overwhelmingly negative reactions from their fans, with many calling for the company to reverse the decision. Additionally, their YouTube channel lost over 50,000 subscribers in the day following the announcement. On April 22, 2024, the company issued an apology and changed their decision, stating that episodes would instead be released on the streaming service a month before their premiere on YouTube. In May 2025, the channel 'Andrew, Steven, and Adam' was launched as a subsidiary of Watcher with the release of the second season of Travel Season. Travel Season is a spiritual successor to Worth It with the same cast of Lim, Andrew Ilnyckyj, and Adam Bianchi. The channel focuses on food reviews and the behind of the scenes of making it. The main channel is now set to be focused primarily on horror, creepy, and paranormal content. == Channels and shows == === Watcher === ==== Current shows ==== Puppet History (2020–present) A whimsical puppet host walks through history's wildest tales as two guests compete for the title of history wizard. Making Watcher (2020–present) What happens when 3 creators with no business experience decide to make their own company? A multi-series documentary on the journey of creating Watcher Entertainment. Weird Wonderful World (2020–present) Curious pals Madej and Bergara explore lesser-known destinations and the fascinating subcultures within them. Too Many Spirits (2020–present) Bergara and Madej read and rate audience-submitted ghost stories, while getting progressively more tipsy drinking cocktails prepared by Steven and Ricky Wang. Top 5 Beatdown (2020–present) Bergara and Madej compare asinine top 5 lists with a topical expert, inspiring surprisingly heated debate. Are You Scared? (2020–2022, 2024–present) Bergara reads the internet's scariest stories (some true, some false) to his pal Madej as they try to figure out if the story is experienced or imagined. Ghost Files (2021–present) Bergara and Madej investigate haunted locations to discover whether something paranormal really lies within. Mystery Files (2023–present) Bergara and Madej present unusual crime or supernatural mysteries with a collection of theoretical solutions. Survival Mode (2023–present) Bergara and Madej play a variety of horror games and give a spooky review. ==== Former shows ==== Grocery Run (2020) Madej interviews a celeb on their typical grocery run, before returning to their home to help prepare their signature dish. Homemade (2020) Lim examines popular food by comparing an elevated restaurant experience vs. a home-cooked experience. Spooky Small Talk (2020) Bergara interviews celebs in a haunted house, exposing their fears and if they can manage it, a little about themselves too. Social Distancing D&D (2020) Socially Distance along with the motley gang of Watchers as they embark on a great quest of Dungeons and Dragons! Tourist Trapped (2020) Begara and Madej battle for tour guide supremacy, highlighting the two sides of a city, tourist attractions and hidden gems. Watcher Weekly (2020–2021) Lim, Bergara, and Madej chat the week's content and answer questions, with the occasional musical guest! Dish Granted (2021–2022) A show where host and amateur home cook Lim attempts to create the most extravagant dishes for his friends. Pretty Historic (2022) Selorm and guests explore beauty and fashion trends from history, try them, and decide whether the trends should remain in the past or come to the present. Worth a Shot (2022–2023) Take a seat at a Master Mixologist's bar as pro Ricky Wang crafts the unbelievable into a digestible drink for his guests. === Watcher Podcast === ==== Current shows ==== Get Scared with Shane, Ryan, and Steven (2023–2025) Previously named 'Pod Watcher' Madej, Bergara, and Lim host a weekly podcasts, exploring a variety of topics and answering viewer questions. Guests occasionally appear to replace one host. Matt Real serves as the producer and a fourth voice for the podcast. For Your Amusement (2023–present) Bergara explores a variety of topics surrounding theme parks. === Andrew, Steven, and Adam === Travel Season (2024–present) Lim reunites with Worth It costars Andrew Ilnyckyj and Adam Bianchi in a new food review show. == Awards and nominations ==
Brain technology
Brain technology, or self-learning know-how systems, defines a technology that employs latest findings in neuroscience. [see also neuro implants] The term was first introduced by the Artificial Intelligence Laboratory in Zurich, Switzerland, in the context of the Roboy project. Brain Technology can be employed in robots, know-how management systems and any other application with self-learning capabilities. In particular, Brain Technology applications allow the visualization of the underlying learning architecture often coined as "know-how maps". == Research and applications == The first demonstrations of BC in humans and animals took place in the 1960s when Grey Walter demonstrated use of non-invasively recorded encephalogram (EEG) signals from a human subject to control a slide projector (Graimann et al., 2010). Soon after Jacques J. Vidal coined the term brain–computer interface (BCI) in 1971, the Defense Advanced Research Projects Agency (DARPA) first starting funding brain–computer interface research and has since funded several brain–computer interface projects. That market is expected to reach a value of $1.72 billion by 2022. Brain–computer interfaces record brain activity, transmit the information out of the body, signal-process the data via algorithms, and convert them into command control signals. In 2012, a landmark study in Nature, led by pioneer Leigh Hochberg, MD, PhD, demonstrated that two people with tetraplegia were able to control robotic arms through thought when connected to the BrainGate neural interface system. The two participants were able to reach for and grasp objects in three-dimensional space, and one participant used the system to serve herself coffee for the first time since becoming paralyzed nearly 15 years prior. And in October 2020, two patients were able to wirelessly control an operating system to text, email, shop and bank using direct thought through the Stentrode brain computer interface (Journal of NeuroInterventional Surgery) in a study led by Thomas Oxley. This was the first time a brain–computer interface was implanted via the patient's blood vessels, eliminating the need for open brain surgery. Currently a number of groups are exploring a range of experimental devices using brain–computer interfaces, which have the potential to fundamentally change the way of life for patients with paralysis and a wide range of neurological disorders. These include: as Elon Musk, Facebook, and the University of California in San Francisco. The systems. This technology is also being explored as a neuromodulation device and may ultimately help diagnose and treat a range of brain pathologies, such as epilepsy and Parkinson's disease.
Data janitor
A data janitor is a person who works to take big data and condense it into useful amounts of information. Also known as a "data wrangler", a data janitor sifts through data for companies in the information technology industry. A multitude of start-ups rely on large amounts of data, so a data janitor works to help these businesses with this basic, but difficult process of interpreting data. While it is a commonly held belief that data janitor work is fully automated, many data scientists are employed primarily as data janitors. The information technology industry has been increasingly turning towards new sources of data gathered on consumers, so data janitors have become more commonplace in recent years.
Information and media literacy
Information and media literacy (IML) is a combination of information literacy and media literacy. It enables people to show and make informed judgments as users of information and media, as well as to become skillful creators and producers of information and media messages. The transformative nature of IML includes creative works and creating new knowledge; to publish and collaborate responsibly requires ethical, cultural and social understanding. IML is also known as media and information literacy (MIL). UNESCO first adopted the term MIL in 2008 as a "composite concept" combining the competencies of information literacy and media literacy. UNESCO emphasizes the importance of global education in media and information literacy, and in 2013 defined Media and Information Literacy (MIL) as the ability to access, evaluate, use, and create information and media content in critical and ethical ways. Prior to the 1990s, the primary focus of information literacy was research skills. Media literacy, a study that emerged around the 1970s, traditionally focuses on the analysis and the delivery of information through various forms of media. Information literacy, as a skill proposed as early as 1974, centers on an individual's ability to recognize information needs and effectively locate, evaluate, and use information. These days, the study of information literacy has been extended to include the study of media literacy in many countries like the UK, Australia and New Zealand. It is also referred to as information and communication technologies (ICT) in the United States. Educators such as Gregory Ulmer have also defined the field as electracy.Media literacy is the ability to actively inquire into and think critically about information. It includes the ability to understand, evaluate, and create media content, and is an essential skill in today's information society. Livingstone, Van Couvering, and Thumim (2008) described the distinction between media literacy and information literacy: "Media literacy views media as lenses or windows for observing the world and expressing the self, whereas information literacy sees information as a tool for taking action in the world." == Integration of media and information literacy == Historically, the fields of information and media literacy have been separate, but over the course of the 21st century there have been calls to integrate both fields. Most definitions of information and media literacy include not only the abilities to locate, access, and analyze information but also the ability to create information. Only by integrating media literacy with information literacy can students better understand the sources of information and how it is used. Media education has primarily taken place in educational institutions, while information education has primarily occurred in libraries. Discussions surrounding the overlap of information literacy and media literacy came to fruition in the mid-to-late 2000s and 2010s as noted by Marcus Leaning. == In the digital age == The definition of literacy is "the ability to read and write". In practice many more skills are needed to locate, critically assess and make effective use of information. By extension, literacy now also includes the ability to manage and interact with digital information and media, in personal, shared and public domains. Historically, "information literacy" has largely been seen from the relatively top-down, organisational viewpoint of library and information sciences. However the same term is also used to describe a generic "information literacy" skill. The modern digital age has led to the proliferation of information spread across the Internet. Individuals must be able to recognize whether information is true or false and better yet know how to locate, evaluate, use, and communicate information in various formats; this is called information literacy. Towards the end of the 20th century, literacy was redefined to include "new literacies" relating to the new skills needed in everyday experience. "Multiliteracies" recognised the multiplicity of literacies, which were often used in combination. "21st century skills" frameworks link new literacies to wider life skills such as creativity, critical thinking, accountability. What these approaches have in common is a focus on the multiple skills needed by individuals to navigate changing personal, professional and public "information landscapes". As the conventional definition of literacy itself continues to evolve among practitioners, so too has the definition of information literacies. Noteworthy definitions include: Zurkowski defined information literacy as "the ability to find known or knowable content on any subject." CILIP, the Chartered Institute of Library and Information Practitioners, defines information literacy as "the ability to think critically and make balanced judgements about any information we find and use". In the United States, the definition proposed by the Association of College and Research Libraries (ACRL) is the most widely recognized. It defines information literacy as "a set of abilities requiring individuals to recognize when information is needed and to locate, evaluate, and use the needed information effectively." JISC, the Joint Information Systems Committee, refers to information literacy as one of six "digital capabilities", seen as an interconnected group of elements centered on "ICT literacy". Mozilla groups digital and other literacies as "21st century skills", a "broad set of knowledge, skills, habits and traits that are important to succeed in today's world". UNESCO, the United Nations Educational, Scientific and Cultural Organization, recognizing the necessity of teaching and learning both traditional and new types of information, the global importance of education was emphasized in 2008 through the "Teacher Media and Information Literacy (MIL) Curriculum". It defines MIL as a set of competencies that enable citizens to access, retrieve, understand, evaluate, use, create, and share information and media content in all formats through various tools in a critical, ethical, and effective manner, so as to participate in and carry out personal, professional, and social activities. Besides this, UNESCO also asserts information literacy as a "universal human right". == 21st-century students == In modern society, although the overall level of education has improved, the channels for knowledge production and dissemination have become increasingly diverse and commercialized, and traditional authoritative institutions no longer hold a monopoly over knowledge validation. While digital platforms have broadened access to information, they have also weakened trust mechanisms and evaluation standards, making epistemological skepticism a norm. Moreover, with the rise and spread of social media, misinformation and disinformation can be just as easily accessed in both densely and sparsely populated areas. These factors further underscore the importance of information literacy education. The IML learning capacities prepare students to be 21st century literate. According to Jeff Wilhelm (2000), "technology has everything to do with literacy. And being able to use the latest electronic technologies has everything to do with being literate." He supports his argument with J. David Bolter's statement that "if our students are not reading and composing with various electronic technologies, then they are illiterate. They are not just unprepared for the future; they are illiterate right now, in our current time and context". In a broader sense, developing this advanced competency of media and information literacy is essential, as it is crucial for students to exercise their freedom of expression in the 21st century. Wilhelm's statement is supported by the 2005 Wired World Phase II (YCWW II) survey conducted by the Media Awareness Network of Canada on 5000 Grade 4 – 11 students. The key findings of the survey were: 62% of Grade 4 students prefer the Internet. 38% of Grade 4 students prefer the library. 91% of Grade 11 students prefer the Internet. 9% of Grade 11 students prefer the library. Marc Prensky (2001) uses the term "digital native" to describe people who have been brought up in a digital world. The Internet has been a pervasive element of young people's home lives. 94% of kids reported that they had Internet access at home, and a significant majority (61%) had a high-speed connection. By the time kids reach Grade 11, half of them (51 percent) have their own Internet-connected computer, separate and apart from the family computer. The survey also showed that young Canadians are now among the most wired in the world. Contrary to the earlier stereotype of the isolated and awkward computer nerd, today's wired kid is a social kid. In general, many students are better networked through the use of technology than most teachers and parents, who may not understand the abilities of technology.
Snap rounding
Snap rounding is a method of approximating line segment locations by creating a grid and placing each point in the centre of a cell (pixel) of the grid. The method preserves certain topological properties of the arrangement of line segments. Drawbacks include the potential interpolation of additional vertices in line segments (lines become polylines), the arbitrary closeness of a point to a non-incident edge, and arbitrary numbers of intersections between input line-segments. The 3 dimensional case is worse, with a polyhedral subdivision of complexity n becoming complexity O(n4). There are more refined algorithms to cope with some of these issues, for example iterated snap rounding guarantees a "large" separation between points and non-incident edges. == Algorithm == ... (please edit). See, and https://www.cgal.org/ () == Properties == Canonicity: Efficiency; A number of efficient implementations exist. Conversely there are undesirable properties: Non-idempotence: Repeated applications can cause arbitrary drift of points. Exception on "Stable snap rounding" algorithms, see https://doi.org/10.1016/j.comgeo.2012.02.011
Semantic interpretation
Semantic interpretation is an important component in dialog systems. It is related to natural language understanding, but mostly it refers to the last stage of understanding. The goal of interpretation is binding the user utterance to concept, or something the system can understand. Typically it is creating a database query based on user utterance.
Lai–Robbins lower bound
The Lai–Robbins lower bound gives an asymptotic lower bound on the regret that any uniformly good algorithm must incur in the stochastic multi-armed bandit problem. The original result was proved by Tze Leung Lai and Herbert Robbins in 1985 for parametric exponential families. Later work extended the statement to more general classes of distributions. == Multi-armed bandit problem == The multi-armed bandit problem (MAB) is a sequential game in which the player must trade off exploration (to learn) and exploitation (to earn). The player chooses among K {\displaystyle K} actions (arms) with unknown distributions ν = ( ν 1 , … , ν K ) {\displaystyle \nu =(\nu _{1},\dots ,\nu _{K})} . The player is assumed to know a class of distributions D {\displaystyle {\mathcal {D}}} such that for every k {\displaystyle k} one has ν k ∈ D {\displaystyle \nu _{k}\in {\mathcal {D}}} (for example, D {\displaystyle {\mathcal {D}}} may be the family of Gaussian or Bernoulli distributions). At each round t = 1 , … , T {\displaystyle t=1,\dots ,T} the player selects (pulls) an arm a t {\displaystyle a_{t}} and observes a reward X t ∼ ν a t {\displaystyle X_{t}\sim \nu _{a_{t}}} . We denote N a ( t ) := ∑ s = 1 t 1 { a s = a } {\displaystyle N_{a}(t):=\sum _{s=1}^{t}\mathbf {1} _{\{a_{s}=a\}}} the number of times arm a {\displaystyle a} has been pulled in the first t {\displaystyle t} rounds, μ ( ν ) := ( μ 1 , … , μ K ) {\displaystyle \mu (\nu ):=(\mu _{1},\dots ,\mu _{K})} the vector of arm means, where μ k = E X ∼ ν k [ X ] {\displaystyle \mu _{k}=\mathbb {E} _{X\sim \nu _{k}}[X]} , μ ∗ := max a μ a {\displaystyle \mu ^{}:=\max _{a}\mu _{a}} the highest mean Δ a := μ ∗ − μ a ≥ 0 {\displaystyle \Delta _{a}:=\mu ^{}-\mu _{a}\geq 0} the gap of arm a {\displaystyle a} . An arm a {\displaystyle a} with μ a = μ ∗ {\displaystyle \mu _{a}=\mu ^{}} is called an optimal arm; otherwise it is a suboptimal arm. The goal is to minimize the regret at horizon T {\displaystyle T} , defined by R T := ∑ a = 1 K Δ a E [ N a ( T ) ] . {\displaystyle R_{T}:=\sum _{a=1}^{K}\Delta _{a}\,\mathbb {E} [N_{a}(T)].} Intuitively, the regret is the (expected) total loss compared to always playing an optimal arm: regret = ∑ a ( cost of playing a ) × ( times a is played ) . {\displaystyle {\text{regret}}=\sum _{a}\ ({\text{cost of playing }}a)\times ({\text{times }}a{\text{ is played}}).} An MAB algorithm is a (possibly randomized) policy that, at each round t {\displaystyle t} , choose an arm a_t by using the observations received from previous turns. === Intuitive example === Suppose a farmer must choose, each year, one of K {\displaystyle K} seed varieties to plant. Each variety k {\displaystyle k} has an unknown average yield μ k {\displaystyle \mu _{k}} . If the farmer knew the best variety (with mean μ ∗ {\displaystyle \mu ^{}} ) he would plant it every year; in reality he must try varieties to learn which is best. The cumulative regret after T {\displaystyle T} years measures the total expected loss in yield due to imperfect knowledge. Remarks The model above is the stochastic MAB; there also exist adversarial variants. One may consider a fixed-horizon setting (known T {\displaystyle T} ) or an anytime setting (unknown T {\displaystyle T} ). == Lai–Robbins lower bound == The theorem gives the right amount of time we should pull a suboptimal arm k {\displaystyle k} to distinguish whether we are in the instance with ν k {\displaystyle \nu _{k}} or with ν ~ k {\displaystyle {\tilde {\nu }}_{k}} where ν ~ k {\displaystyle {\tilde {\nu }}_{k}} is such that μ ~ k > μ ∗ {\displaystyle {\tilde {\mu }}_{k}>\mu ^{}} . Knowning a lower bound on the number of pull of every suboptimal arm gives a lower bound on the regret as only suboptimal arms contribute to the regret. Before stating the formal theorem we need to define what is a consistent algorithm. === Consistency (uniformly good algorithms) === Let D {\displaystyle {\mathcal {D}}} be a class of probability distributions and consider K {\displaystyle K} arms with reward distributions ν = ( ν 1 , … , ν K ) ∈ D K {\displaystyle \nu =(\nu _{1},\dots ,\nu _{K})\in {\mathcal {D}}^{K}} . An algorithm is said to be consistent (also called uniformly good) on D K {\displaystyle {\mathcal {D}}^{K}} if, for every instance ν ∈ D K {\displaystyle \nu \in {\mathcal {D}}^{K}} , the expected regret R T ( ν ) {\displaystyle R_{T}(\nu )} grows subpolynomially: ∀ α > 0 , R T ( ν ) = o ( T α ) as T → ∞ {\displaystyle \forall \alpha >0,\qquad R_{T}(\nu )=o(T^{\alpha })\quad {\text{as }}T\to \infty } This assumption excludes algorithms that perform well on some instances but incur linear regret on others. === Formal lower bound === For any suboptimal arm a {\displaystyle a} . For a distribution ν a ∈ D {\displaystyle \nu _{a}\in {\mathcal {D}}} and a threshold x {\displaystyle x} , define K inf ( ν a , x , D ) := inf { KL ( ν a , ν ′ ) : ν ′ ∈ D , μ ′ > x } {\displaystyle {\mathcal {K}}_{\inf }(\nu _{a},x,{\mathcal {D}}):=\inf {\Bigl \{}\operatorname {KL} (\nu _{a},\nu '):\nu '\in {\mathcal {D}},\ \mu '>x{\Bigr \}}} where KL ( ⋅ , ⋅ ) {\displaystyle \operatorname {KL} (\cdot ,\cdot )} denotes the Kullback-Leibler divergence. Then, for any algorithm consistent on D K {\displaystyle {\mathcal {D}}^{K}} and for every instance ν ∈ D K {\displaystyle \nu \in {\mathcal {D}}^{K}} , every suboptimal arm a {\displaystyle a} satisfies E ν [ N a ( T ) ] ≥ ln T K inf ( ν a , μ ∗ , D ) + o ( ln T ) {\displaystyle \mathbb {E} _{\nu }[N_{a}(T)]\geq {\frac {\ln T}{{\mathcal {K}}_{\inf }(\nu _{a},\mu ^{},{\mathcal {D}})}}+o(\ln T)} Consequently, the regret satisfies R T ( ν ) ≥ ( ∑ a : μ a < μ ∗ Δ a K inf ( ν a , μ ∗ , D ) ) ln T + o ( ln T ) {\displaystyle R_{T}(\nu )\geq \left(\sum _{a:\,\mu _{a}<\mu ^{}}{\frac {\Delta _{a}}{{\mathcal {K}}_{\inf }(\nu _{a},\mu ^{},{\mathcal {D}})}}\right)\ln T+o(\ln T)} The original 1985 paper established this result for exponential families; later work showed that the bound holds under much weaker assumptions on D {\displaystyle {\mathcal {D}}} . === Intuition === Consistency imposes that, for every ν {\displaystyle \nu } , the number of pulls of an optimal arm must be large. This means that μ ∗ {\displaystyle \mu ^{}} is estimated very accurately. The goal is to determine, for a suboptimal arm k {\displaystyle k} , how many samples are needed to be confident, with the appropriate level of confidence, that μ k < μ ∗ {\displaystyle \mu _{k}<\mu ^{}} . To do so, we use what is called the most confusing instance: an instance close to ν {\displaystyle \nu } such that arm k {\displaystyle k} is optimal. We define it as ν ~ {\displaystyle {\tilde {\nu }}} such that, for all a ≠ k {\displaystyle a\neq k} , ν ~ a = ν a {\displaystyle {\tilde {\nu }}_{a}=\nu _{a}} , and ν ~ k {\displaystyle {\tilde {\nu }}_{k}} is chosen so that μ ~ k > μ ∗ {\displaystyle {\tilde {\mu }}_{k}>\mu ^{}} . The objective is to determine how many samples of arm k {\displaystyle k} are required to distinguish whether we are in the instance with ν k {\displaystyle \nu _{k}} or with ν ~ k {\displaystyle {\tilde {\nu }}_{k}} in terms of KL {\displaystyle \operatorname {KL} } distance. == Algorithms achieving the Lai–Robbins lower bound == Several algorithms are known to achieve the Lai–Robbins asymptotic lower bound under specific assumptions on the reward distribution class D {\displaystyle {\mathcal {D}}} . The following list summarizes a non-exhaustive list of algorithms matching the lower bound. == Extension to other problems == === Structured bandit === A more complexe is structured bandit where we know that the mean of each arm is in a set with some restriction. In this case we can prove a smaller lower bound that use the knowledge of this set. === Best arm identification (BAI) === A similar result has been proved for best arm identification, which is the same game except that, instead of minimizing the regret, the goal is to identify the best arm with probability 1 − δ {\displaystyle 1-\delta } using as few rounds as possible. === Reinforcement Learning (RL) === Similar results have been proved for regret minimization in average-reward reinforcement learning. The order is also ln T {\displaystyle \ln T} , with a constant that depends on the problem.