TD-Gammon is a computer backgammon program developed in the 1990s by Gerald Tesauro at IBM's Thomas J. Watson Research Center. Its name comes from the fact that it is an artificial neural net trained by a form of temporal-difference learning, specifically TD-Lambda. It explored strategies that humans had not pursued and led to advances in the theory of correct backgammon play. In 1993, TD-Gammon (version 2.1) was trained with 1.5 million games of self-play, and achieved a level of play just slightly below that of the top human backgammon players of the time. In 1998, during a 100-game series, it was defeated by the world champion by a mere margin of 8 points. Its unconventional assessment of some opening strategies had been accepted and adopted by expert players. TD-gammon is commonly cited as an early success of reinforcement learning and neural networks, and was cited in, for example, papers for deep Q-learning and AlphaGo. == Algorithm for play and learning == During play, TD-Gammon examines on each turn all possible legal moves and all their possible responses (lookahead search), feeds each resulting board position into its evaluation function, and chooses the move that leads to the board position that got the highest score. In this respect, TD-Gammon is no different than almost any other computer board-game program. TD-Gammon's innovation was in how it learned its evaluation function. TD-Gammon's learning algorithm consists of updating the weights in its neural net after each turn to reduce the difference between its evaluation of previous turns' board positions and its evaluation of the present turn's board position—hence "temporal-difference learning". The score of any board position is a set of four numbers reflecting the program's estimate of the likelihood of each possible game result: White wins normally, Black wins normally, White wins a gammon, Black wins a gammon. For the final board position of the game, the algorithm compares with the actual result of the game rather than its own evaluation of the board position. The core of TD-gammon is a neural network with 3 layers. The input layer has two types of neurons. One type codes for the board position. They are non-negative integers ranging from 0 to 15, indicating the number of White or Black checkers at each board location. There are 99 input neurons for each, totaling 198 neurons. Another type codes for hand-crafted features previously used in Neurogammon. These features encoded standard concepts used by human experts, such as "advanced anchor," "blockade strength," "home board strength" and the probability of a "blot" (single checker) being hit. The hidden layer contains hidden neurons. Later versions had more of these. The output layer contains 4 neurons, representing the network's estimate of the probability ("equity") that the current board would lead to. The 4 neurons code for: White normal win, White gammon win, Black normal win, Black gammon win. Backgammon win is so rare that Tesauro opted to not represent it. After each turn, the learning algorithm updates each weight in the neural net according to the following rule: w t + 1 − w t = α ( Y t + 1 − Y t ) ∑ k = 1 t λ t − k ∇ w Y k {\displaystyle w_{t+1}-w_{t}=\alpha (Y_{t+1}-Y_{t})\sum _{k=1}^{t}\lambda ^{t-k}\nabla _{w}Y_{k}} where: It was found that picking small λ {\displaystyle \lambda } offered performance roughly equally good, and large λ {\displaystyle \lambda } degraded performance. Because of this, after 1992, TD-Gammon was trained with λ = 0 {\displaystyle \lambda =0} , degenerating into standard TD-learning. This saved compute by a factor of 2. == Development history == Version 1.0 used simple 1-ply search: every next move is scored by the neural net, and the highest-scoring move is selected. Versions 2.0 and 2.1 used 2-ply search: Make a 1-ply analysis to remove unlikely moves ("forward pruning"). Make a 2-play minimax analysis for only the likely moves. Pick the best move, probability-weighted by each of the opponent's 21 possible dice rolls (weighting non-doubles twice as much as doubles). Versions 3.0 and 3.1 used 3-ply search, using 21 2 = 441 {\displaystyle 21^{2}=441} possible dice rolls instead of 21. The last version, 3.1, was trained specifically for an exhibition match against Malcolm Davis at the 1998 AAAI Hall of Champions. It lost at -8 points, mainly due to one blunder, where TD-Gammon opted to double and got gammoned at -32 points. == Experiments and stages of training == Unlike previous neural-net backgammon programs such as Neurogammon (also written by Tesauro), where an expert trained the program by supplying the "correct" evaluation of each position, TD-Gammon was at first programmed "knowledge-free". In early experimentation, using only a raw board encoding with no human-designed features, TD-Gammon reached a level of play comparable to Neurogammon: that of an intermediate-level human backgammon player. Even though TD-Gammon discovered insightful features on its own, Tesauro wondered if its play could be improved by using hand-designed features like Neurogammon's. Indeed, the self-training TD-Gammon with expert-designed features soon surpassed all previous computer backgammon programs. It stopped improving after about 1,500,000 games (self-play) using a three-layered neural network, with 198 input units encoding expert-designed features, 80 hidden units, and one output unit representing predicted probability of winning. == Advances in backgammon theory == TD-Gammon's exclusive training through self-play (rather than imitation learning) enabled it to explore strategies that humans previously had not considered or had ruled out erroneously. Its success with unorthodox strategies had a significant impact on the backgammon community. Late 1991, Bill Robertie, Paul Magriel, and Malcolm Davis, were invited to play against TD-Gammon (version 1.0). A total of 51 games were played, with TD-Gammon losing at -0.25 ppg. Robertie found TD-Gammon to be at the level of a competent advanced player, and better than any previous backgammon program. Robertie subsequently wrote about the use of TD-Gammon for backgammon study. For example, on the opening play, the conventional wisdom was that given a roll of 2-1, 4-1, or 5-1, White should move a single checker from point 6 to point 5. Known as "slotting", this technique trades the risk of a hit for the opportunity to develop an aggressive position. TD-Gammon found that the more conservative play of splitting 24-23 was superior. Tournament players began experimenting with TD-Gammon's move, and found success. Within a few years, slotting had disappeared from tournament play, replaced by splitting, though in 2006 it made a reappearance for 2-1. Backgammon expert Kit Woolsey found that TD-Gammon's positional judgement, especially its weighing of risk against safety, was superior to his own or any human's. TD-Gammon's excellent positional play was undercut by occasional poor endgame play. The endgame requires a more analytical approach, sometimes with extensive lookahead. TD-Gammon's limitation to two-ply lookahead put a ceiling on what it could achieve in this part of the game. TD-Gammon's strengths and weaknesses were the opposite of symbolic artificial intelligence programs and most computer software in general: it was good at matters that require an intuitive "feel" but bad at systematic analysis. It is also poor at doubling strategies. This is likely due to the fact that the neural network is trained without the doubling cube, with the doubling added by feeding the neural network's cubeless equity estimates into theoretically-based heuristic formulae. This was particularly the case in the 1998 exhibition match, where it played 100 games against Malcolm Davis. A single doubling blunder lost the match. TD-gammon was never commercialized or released to the public in some other form, but it inspired commercial backgammon programs based on neural networks, such as JellyFish (1994) and Snowie (1998).
Interactions Corporation
Interactions LLC (also known as Interactions Corporation) is an American software company that develops voice and text-based virtual assistant applications for customer-service contact centers. Since September 2025, it has been a subsidiary of SoundHound AI. == History == Interactions was founded in 2004. In July 2011, the company announced a $12 million venture-capital funding round led by Sigma Partners. In November 2014, AT&T sold its "Watson" speech recognition platform and related patents to Interactions in exchange for equity. In May 2017, Interactions acquired the social media customer-engagement company Digital Roots; financial terms were not disclosed. On September 3, 2025, SoundHound AI completed its acquisition of Interactions Corporation, with the acquired company becoming a wholly owned subsidiary. == Products and services == Interactions' products have been described as automated voice portals and intelligent virtual assistants used for customer-service tasks. In 2011, Humana expanded the use of an Interactions voice portal for Medicare Part D enrollment.
Agents of S.H.I.E.L.D. season 4
The fourth season of the American television series Agents of S.H.I.E.L.D., based on the Marvel Comics spy organization S.H.I.E.L.D., follows Phil Coulson and other S.H.I.E.L.D. agents and allies after the signing of the Sokovia Accords. It is set in the Marvel Cinematic Universe (MCU) and acknowledges the continuity of the franchise's films. The season was produced by ABC Studios, Marvel Television, and Mutant Enemy Productions, with Jed Whedon, Maurissa Tancharoen, and Jeffrey Bell serving as showrunners. Clark Gregg reprises his role as Coulson from the film series, starring alongside the returning series regulars Ming-Na Wen, Chloe Bennet, Iain De Caestecker, Elizabeth Henstridge, and Henry Simmons. They are joined by John Hannah who was promoted from his recurring guest role in the third season. The fourth season was ordered in March 2016, with production taking place from that July until the following April. Due to its broadcast schedule, the season was split into three "pods": Ghost Rider for the first eight episodes, featuring recurring guest star Gabriel Luna as the supernatural Robbie Reyes / Ghost Rider and exploring mysticism in the MCU alongside the film Doctor Strange (2016); LMD, referring to the new Life Model Decoy program, for the next seven episodes which focus on recurring guest star Mallory Jansen as the LMD Aida; and Agents of Hydra for the final seven episodes, partly set in a "what if" virtual reality that allowed the return of former series regular Brett Dalton as Grant Ward. The season is also affected by the events of the film Captain America: Civil War (2016), and continues storylines established in the canceled series Agent Carter. The first episode premiered at a screening on September 19, 2016, with the season then airing for 22 episodes on ABC, from September 20, 2016, until May 16, 2017. The premiere debuted to 3.58 million viewers, down from previous season premieres but average for the series. Critical response to the season was positive, with many feeling that each pod was better than the last and in particular praising the visual effects and tone of Ghost Rider, the writing and acting of LMD, and the character development and political commentary explored during Agents of Hydra. The season saw series low viewership, but was still considered to have solved ABC's problem during its new Tuesday night timeslot, and the series was renewed for a fifth season in May 2017. == Episodes == == Cast and characters == == Production == === Development === Agents of S.H.I.E.L.D. was renewed for a fourth season on March 3, 2016, earlier than usual for the series. Executive producer Jed Whedon said on this, "We're thrilled to know going into the end of [season three] with certainty that we will be returning, because we can build our story accordingly." Executive producer Maurissa Tancharoen also noted that logistics for hiring directors for the season in advance would be easier, "which is a very nice privilege to have...that's a luxury". The end of the episode "What If..." features an onscreen tribute to Bill Paxton, who died in February 2017 and had portrayed John Garrett in the series' first season. The series paid additional tribute to Paxton in "All the Madame's Men" with promos during The Bakshi Report news segment showcasing John Garrett as a fallen American hero. The end of "World's End" features a similar onscreen tribute to Powers Boothe, who died in May 2017 and had portrayed Gideon Malick in the series' third season. === Writing === The season shifted to the later 10 pm timeslot, allowing it to take on a darker, more mature tone than previous seasons. According to Tancharoen, "The whole tagline for this year is 'Agents of S.H.I.E.L.D. After Dark'". The timeslot gave the series the opportunity to present an increased level of violence and partial nudity, as well as take more risks and present edgier themes. Following the third-season finale, Tancharoen stated that the fourth season would explore the guilt Daisy Johnson has over Lincoln Campbell's death. Executive producer Jeffrey Bell noted the writers tried to continue the tradition of "finding new combinations and new conflicts" between different sets of characters, given "a lot of procedurals [see] the same people doing the same thing for five years". Pairings that would be explored included Coulson and Mack, continuing from the end of season three, who have a mutual respect for one another due to their relationships with Daisy, and Leo Fitz and Holden Radcliffe, who work together. The Fitz-Simmons relationship was also explored more, examining the new challenges it presented for the two "working together, loving each other and living together". Following the third season's dealing with the themes of Captain America: Civil War (2016), such as the opposing reactions to the Inhumans, Whedon said that the question of "How do you deal with a war with powered people at that level, a government level?" was one that they wanted to answer in the fourth season. Tancharoen called the Inhumans "a permanent part of our universe now", with Whedon adding, "we have a quick-fire way of introducing people with powers. It gives us a lot of leeway in our world, and it lets us explore the metaphors of what it is like to be different. We will never close that chapter." With the Inhumans film being removed from Marvel Studios' release schedule, the series had "a little more freedom" and were "able to do a little bit more" with the species, including the potential of introducing some of the "classic" Inhumans, though the series would focus less on Inhumans than the third season which saw "a real significant Inhuman agenda story". It was not intended to be a spin-off of Agents of S.H.I.E.L.D. On the evolution of S.H.I.E.L.D. to featuring so many powered characters, Whedon said "the dynamic in the world has changed. There was one person with powers, and then by The Avengers there were maybe six total ... now they're much more prevalent, so there's reaction from the public based on that." The season is structured into three "pods" based on its airing schedule: the first eight episodes, subtitled Ghost Rider; LMD (Life Model Decoy) for the subsequent seven episodes; and a third pod for the final seven episodes called Agents of Hydra. Elements and characters cross over between the different pods, but the sections "definitely have a different feel" from one another, as Bell explained that 22 episodes "is a long time to hold a big bad or a single plot line, especially for an audience", and for the past two seasons, the series was able to have two separated halves that "allows us to introduce a big bad. And then, something happens and we rise somebody new ... Now, there's three of those." "Financial considerations" were also taken into account in creating the pods for the season, as using LMDs does not "cost as much as setting a guy's head on fire via CGI". In terms of writing the "complicated season", Whedon said the writers were "aware that our fans are our fans and have spent some time with these characters and are clever and see things coming sometimes ... Part of our job is to create not just what we are presenting on plot, but letting the audience be one step ahead of us and being one step ahead of that." He added that the writers knew that they wanted to tell a Ghost Rider story, an LMD story, and a "what if" scenario, and the hardest part was making each pod still fit together as a single season. The major connection ultimately became the Darkhold, which leads from the magic of Ghost Rider to the advanced science of LMD and then the Framework in Agents of Hydra. Ghost Rider also reappears in the final episode of the season, "World's End", as an additional connection. ==== Ghost Rider ==== While planning the fourth season, Marvel suggested that the series introduce Ghost Rider, after the character's film rights had returned to Marvel from Sony in May 2013. Loeb felt that this made the season unquestionably "the series' biggest" with the "most ambitious story yet". He added that "one of the things that we talked about is, S.H.I.E.L.D. always looked out for the weird, the unusual, the things that were and could be a problem for the public", and Marvel realized that Ghost Rider's abilities, which are more mystical than anything seen in the series to date, opened up "a quarter of the universe that we haven't really spent a lot of time exploring ... what happens if our very real, our very grounded agents who are very much a family have to take on something that is as bizarre and powerful and unique as Ghost Rider." Bell added that the producers would have been willing to give an entire season of the show to a Ghost Rider arc if the season was 13 episodes or less, but 22 episodes seemed too long to "feel like one flavor". The Robbie Reyes version of Ghost Rider was chosen over other versions of the character from the comics because of his relationship with his brother Gabe, w
Agent2Agent
Agent2Agent (A2A) is an open protocol that defines how artificial intelligence agents communicate with each other across different systems. It is intended to allow agents built by different vendors or frameworks to discover one another, exchange messages, and coordinate tasks. == History == The Agent2Agent protocol was announced by Google in April 2025 as an open standard for agent interoperability. In June 2025, Google transferred the protocol, its specification, and related software development kits to the Linux Foundation. The Linux Foundation established the Agent2Agent project to provide vendor-neutral governance. == Design == The A2A protocol supports communication between autonomous software agents operating across different platforms and organizations. It enables agents to discover one another and exchange structured messages without requiring shared internal state or proprietary integrations. A2A uses metadata documents, known as Agent Cards, to describe an agent's capabilities and how it can be accessed. These documents are exchanged using widely adopted web technologies such as HTTP and JSON-based messaging formats. A2A includes support for authentication and authorization to control which agents may participate in workflows. The protocol supports established security technologies including Transport Layer Security (TLS), JSON Web Tokens (JWTs), and OpenID Connect. A2A is often discussed alongside the Model Context Protocol (MCP). MCP focuses on connecting agents to tools and data sources, while A2A focuses on communication between agents themselves. == Adoption == At the time the Linux Foundation adopted the protocol, more than 100 technology companies had announced support for the Agent2Agent project. Microsoft stated that it planned to support the protocol in its AI platforms. == Reception == Technology press coverage has described A2A as an attempt to reduce fragmentation in AI agent ecosystems by providing a shared communication layer. TechRepublic characterized the protocol as part of a broader industry effort to reduce vendor lock-in for enterprise AI systems.
History of artificial life
Humans have considered and tried to create non-biological life for at least 3,000 years. As seen in tales ranging from Pygmalion to Frankenstein, humanity has long been intrigued by the concept of artificial life. == Pre-computer == The earliest examples of artificial life involve sophisticated automata constructed using pneumatics, mechanics, and/or hydraulics. The first automata were conceived during the third and second centuries BC and these were demonstrated by the theorems of Hero of Alexandria, which included sophisticated mechanical and hydraulic solutions. Many of his notable works were included in the book Pneumatics, which was also used for constructing machines until early modern times. In 1490, Leonardo da Vinci also constructed an armored knight, which is considered the first humanoid robot in Western civilization. Other early famous examples include al-Jazari's humanoid robots. This Arabic inventor once constructed a band of automata, which can be commanded to play different pieces of music. There is also the case of Jacques de Vaucanson's artificial duck exhibited in 1735, which had thousands of moving parts and one of the first to mimic a biological system. The duck could reportedly eat and digest, drink, quack, and splash in a pool. It was exhibited all over Europe until it fell into disrepair. In the late 1600s, following René Descartes' claims that animals could be understood as purely physical machines, there was increasing interest in the question of whether a machine could be designed that, like an animal, could generate offspring (a self-replicating machine). However, it wasn't until the invention of cheap computing power that artificial life as a legitimate science began in earnest, steeped more in the theoretical and computational than the mechanical and mythological. == 1950s–1970s == One of the earliest thinkers of the modern age to postulate the potentials of artificial life, separate from artificial intelligence, was math and computer prodigy John von Neumann. At the Hixon Symposium, hosted by Linus Pauling in Pasadena, California in the late 1940s, von Neumann delivered a lecture titled "The General and Logical Theory of Automata." He defined an "automaton" as any machine whose behavior proceeded logically from step to step by combining information from the environment and its own programming, and said that natural organisms would in the end be found to follow similar simple rules. He also spoke about the idea of self-replicating machines. He postulated a made-up of a control computer, a construction arm, and a long series of instructions, floating in a lake of parts. By following the instructions that were part of its own body, it could create an identical machine. He followed this idea by creating (with Stanislaw Ulam) a purely logic-based automaton, not requiring a physical body but based on the changing states of the cells in an infinite grid – the first cellular automaton. It was extraordinarily complicated compared to later CAs, having hundreds of thousands of cells which could each exist in one of twenty-nine states, but von Neumann felt he needed the complexity in order for it to function not just as a self-replicating "machine", but also as a universal computer as defined by Alan Turing. This "universal constructor" read from a tape of instructions and wrote out a series of cells that could then be made active to leave a fully functional copy of the original machine and its tape. Von Neumann worked on his automata theory intensively right up to his death, and considered it his most important work. Homer Jacobson illustrated basic self-replication in the 1950s with a model train set – a seed "organism" consisting of a "head" and "tail" boxcar could use the simple rules of the system to consistently create new "organisms" identical to itself, so long as there was a random pool of new boxcars to draw from. Edward F. Moore proposed "Artificial Living Plants", which would be floating factories which could create copies of themselves. They could be programmed to perform some function (extracting fresh water, harvesting minerals from seawater) for an investment that would be relatively small compared to the huge returns from the exponentially growing numbers of factories. Freeman Dyson also studied the idea, envisioning self-replicating machines sent to explore and exploit other planets and moons, and a NASA group called the Self-Replicating Systems Concept Team performed a 1980 study on the feasibility of a self-building lunar factory. University of Cambridge professor John Horton Conway invented the most famous cellular automaton in the 1960s. He called it the Game of Life, and publicized it through Martin Gardner's column in Scientific American magazine. Norwegian-Italian mathematician Nils Aall Barricelli, who worked mainly at US institutions, was a pioneer in computer based simulation of biological processes such as symbiogenesis and evolution. == 1970s–1980s == Philosophy scholar Arthur Burks, who had worked with von Neumann (and indeed, organized his papers after Neumann's death), headed the Logic of Computers Group at the University of Michigan. He brought the overlooked views of 19th century American thinker Charles Sanders Peirce into the modern age. Peirce was a strong believer that all of nature's workings were based on logic (though not always deductive logic). The Michigan group was one of the few groups still interested in alife and CAs in the early 1970s; one of its students, Tommaso Toffoli argued in his PhD thesis that the field was important because its results explain the simple rules that underlay complex effects in nature. Toffoli later provided a key proof that CAs were reversible, just as the true universe is considered to be. Christopher Langton was an unconventional researcher, with an undistinguished academic career that led him to a job programming DEC mainframes for a hospital. He became enthralled by Conway's Game of Life, and began pursuing the idea that the computer could emulate living creatures. After years of study, he began attempting to actualize Von Neumann's CA and the work of Edgar F. Codd, who had simplified Von Neumann's original twenty-nine state monster to one with only eight states. He succeeded in creating the first self-replicating computer organism in October 1979, using only an Apple II desktop computer. He entered Burks' graduate program at the Logic of Computers Group in 1982, at the age of 33, and helped to found a new discipline. Langton's official conference announcement of Artificial Life I was the earliest description of a field which had previously barely existed: Artificial life is the study of artificial systems that exhibit behavior characteristic of natural living systems. It is the quest to explain life in any of its possible manifestations, without restriction to the particular examples that have evolved on earth. This includes biological and chemical experiments, computer simulations, and purely theoretical endeavors. Processes occurring on molecular, social, and evolutionary scales are subject to investigation. The ultimate goal is to extract the logical form of living systems. Microelectronic technology and genetic engineering will soon give us the capability to create new life forms in silico as well as in vitro. This capacity will present humanity with the most far-reaching technical, theoretical and ethical challenges it has ever confronted. The time seems appropriate for a gathering of those involved in attempts to simulate or synthesize aspects of living systems. Ed Fredkin founded the Information Mechanics Group at MIT, which united Toffoli, Norman Margolus, and Charles Bennett. This group created a computer especially designed to execute cellular automata, eventually reducing it to the size of a single circuit board. This "cellular automata machine" allowed an explosion of alife research among scientists who could not otherwise afford sophisticated computers. In 1982, computer scientist named Stephen Wolfram turned his attention to cellular automata. He explored and categorized the types of complexity displayed by one-dimensional CAs, and showed how they applied to natural phenomena such as the patterns of seashells and the nature of plant growth. Norman Packard, who worked with Wolfram at the Institute for Advanced Study, used CAs to simulate the growth of snowflakes, following very basic rules. Computer animator Craig Reynolds similarly used three simple rules to create recognizable flocking behaviour in a computer program in 1987 to animate groups of boids. With no top-down programming at all, the boids produced lifelike solutions to evading obstacles placed in their path. Computer animation has continued to be a key commercial driver of alife research as the creators of movies attempt to find more realistic and inexpensive ways to animate natural forms such as plant life, animal movement, hair growth, and complicated org
Google Clips
Google Clips is a discontinued miniature clip-on camera device developed by Google. == History == It was announced on October 4, 2017 and went on sale on January 27, 2018. Google Clips automatically captured video clips (without audio) at moments its machine learning algorithms determined to be interesting or relevant. An indicator flashed when the camera was looking for scenes to capture. Google Clips' artificial intelligence (AI) could learn the faces of people to take photographs with certain people, and could automatically set lighting and framing. It had 16 GB of storage built-in storage and could record clips for up to 3 hours. This camera was originally priced at US$249 in the United States. It was withdrawn from sale on October 15, 2019, but supported until the end of December 2021. == Reception == The Independent wrote that Google Clips is "an impressive little device, but one that also has the potential to feel very creepy." According to The Verge's generally negative review, "it didn't capture anything special" over two weeks of testing.
Question (short story)
"Question" is a science fiction short story by American writer Isaac Asimov. The story first appeared in the March 1955 issue of Computers and Automation (thought to be the first computer magazine), and was reprinted in the April 30, 1957, issue of Science World. It is the first of a loosely connected series of stories concerning a fictional supercomputer called Multivac. The story concerns two technicians who are servicing Multivac, and their argument over whether or not the machine is truly intelligent and able to think. Multivac, however, supplies the answer on its own. After the reprint, another author, Robert Sherman Townes, noticed the climax in the last sentence was very similar to one of his own stories, "Problem for Emmy" (Startling Stories, June 1952), and wrote to Asimov about it. After searching in his library, Asimov did find the original story and, although he did not recall having read it, admitted that the endings were pretty similar. He then replied to Townes, apologizing and promising the story would never again be published, and it never was. Asimov mentioned "Question" in an editorial called "Plagiarism" which appeared in the August 1985 issue of Asimov's Science Fiction (although he did not mention Townes' name or the title of either story). "Plagiarism" was reprinted in Asimov's collection Gold (1995).