Computer-aided software engineering (CASE) is a domain of software tools used to design and implement applications. CASE tools are similar to and are partly inspired by computer-aided design (CAD) tools used for designing hardware products. CASE tools are intended to help develop high-quality, defect-free, and maintainable software. CASE software was often associated with methods for the development of information systems together with automated tools that could be used in the software development process. == History == The Information System Design and Optimization System (ISDOS) project, started in 1968 at the University of Michigan, initiated a great deal of interest in the whole concept of using computer systems to help analysts in the very difficult process of analysing requirements and developing systems. Several papers by Daniel Teichroew fired a whole generation of enthusiasts with the potential of automated systems development. His Problem Statement Language / Problem Statement Analyzer (PSL/PSA) tool was a CASE tool although it predated the term. Another major thread emerged as a logical extension to the data dictionary of a database. By extending the range of metadata held, the attributes of an application could be held within a dictionary and used at runtime. This "active dictionary" became the precursor to the more modern model-driven engineering capability. However, the active dictionary did not provide a graphical representation of any of the metadata. It was the linking of the concept of a dictionary holding analysts' metadata, as derived from the use of an integrated set of techniques, together with the graphical representation of such data that gave rise to the earlier versions of CASE. The next entrant into the market was Excelerator from Index Technology in Cambridge, Mass. While DesignAid ran on Convergent Technologies and later Burroughs Ngen networked microcomputers, Index launched Excelerator on the IBM PC/AT platform. While, at the time of launch, and for several years, the IBM platform did not support networking or a centralized database as did the Convergent Technologies or Burroughs machines, the allure of IBM was strong, and Excelerator came to prominence. Hot on the heels of Excelerator were a rash of offerings from companies such as Knowledgeware (James Martin, Fran Tarkenton and Don Addington), Texas Instrument's CA Gen and Andersen Consulting's FOUNDATION toolset (DESIGN/1, INSTALL/1, FCP). CASE tools were at their peak in the early 1990s. According to the PC Magazine of January 1990, over 100 companies were offering nearly 200 different CASE tools. At the time IBM had proposed AD/Cycle, which was an alliance of software vendors centered on IBM's Software repository using IBM DB2 in mainframe and OS/2: The application development tools can be from several sources: from IBM, from vendors, and from the customers themselves. IBM has entered into relationships with Bachman Information Systems, Index Technology Corporation, and Knowledgeware wherein selected products from these vendors will be marketed through an IBM complementary marketing program to provide offerings that will help to achieve complete life-cycle coverage. With the decline of the mainframe, AD/Cycle and the Big CASE tools died off, opening the market for the mainstream CASE tools of today. Many of the leaders of the CASE market of the early 1990s ended up being purchased by Computer Associates, including IEW, IEF, ADW, Cayenne, and Learmonth & Burchett Management Systems (LBMS). The other trend that led to the evolution of CASE tools was the rise of object-oriented methods and tools. Most of the various tool vendors added some support for object-oriented methods and tools. In addition new products arose that were designed from the bottom up to support the object-oriented approach. Andersen developed its project Eagle as an alternative to Foundation. Several of the thought leaders in object-oriented development each developed their own methodology and CASE tool set: Jacobson, Rumbaugh, Booch, etc. Eventually, these diverse tool sets and methods were consolidated via standards led by the Object Management Group (OMG). The OMG's Unified Modelling Language (UML) is currently widely accepted as the industry standard for object-oriented modeling. == CASE software == === Tools === CASE tools support specific tasks in the software development life-cycle. They can be divided into the following categories: Business and analysis modeling: Graphical modeling tools. E.g., E/R modeling, object modeling, etc. Development: Design and construction phases of the life-cycle. Debugging environments. E.g., IISE LKO. Verification and validation: Analyze code and specifications for correctness, performance, etc. Configuration management: Control the check-in and check-out of repository objects and files. E.g., SCCS, IISE. Metrics and measurement: Analyze code for complexity, modularity (e.g., no "go to's"), performance, etc. Project management: Manage project plans, task assignments, scheduling. Another common way to distinguish CASE tools is the distinction between Upper CASE and Lower CASE. Upper CASE Tools support business and analysis modeling. They support traditional diagrammatic languages such as ER diagrams, Data flow diagram, Structure charts, Decision Trees, Decision tables, etc. Lower CASE Tools support development activities, such as physical design, debugging, construction, testing, component integration, maintenance, and reverse engineering. All other activities span the entire life-cycle and apply equally to upper and lower CASE. === Workbenches === Workbenches integrate two or more CASE tools and support specific software-process activities. Hence they achieve: A homogeneous and consistent interface (presentation integration) Seamless integration of tools and toolchains (control and data integration) An example workbench is Microsoft's Visual Basic programming environment. It incorporates several development tools: a GUI builder, a smart code editor, debugger, etc. Most commercial CASE products tended to be such workbenches that seamlessly integrated two or more tools. Workbenches also can be classified in the same manner as tools; as focusing on Analysis, Development, Verification, etc. as well as being focused on the upper case, lower case, or processes such as configuration management that span the complete life-cycle. === Environments === An environment is a collection of CASE tools or workbenches that attempts to support the complete software process. This contrasts with tools that focus on one specific task or a specific part of the life-cycle. CASE environments are classified by Fuggetta as follows: Toolkits: Loosely coupled collections of tools. These typically build on operating system workbenches such as the Unix Programmer's Workbench or the VMS VAX set. They typically perform integration via piping or some other basic mechanism to share data and pass control. The strength of easy integration is also one of the drawbacks. Simple passing of parameters via technologies such as shell scripting can't provide the kind of sophisticated integration that a common repository database can. Fourth generation: These environments are also known as 4GL standing for fourth generation language environments due to the fact that the early environments were designed around specific languages such as Visual Basic. They were the first environments to provide deep integration of multiple tools. Typically these environments were focused on specific types of applications. For example, user-interface driven applications that did standard atomic transactions to a relational database. Examples are Informix 4GL, and Focus. Language-centered: Environments based on a single often object-oriented language such as the Symbolics Lisp Genera environment or VisualWorks Smalltalk from Parcplace. In these environments all the operating system resources were objects in the object-oriented language. This provides powerful debugging and graphical opportunities but the code developed is mostly limited to the specific language. For this reason, these environments were mostly a niche within CASE. Their use was mostly for prototyping and R&D projects. A common core idea for these environments was the model–view–controller user interface that facilitated keeping multiple presentations of the same design consistent with the underlying model. The MVC architecture was adopted by the other types of CASE environments as well as many of the applications that were built with them. Integrated: These environments are an example of what most IT people tend to think of first when they think of CASE. Environments such as IBM's AD/Cycle, Andersen Consulting's FOUNDATION, the ICL CADES system, and DEC Cohesion. These environments attempt to cover the complete life-cycle from analysis to maintenance and provide an integrated database repository for storing all artifacts of the software pr
Owain Evans
Owain Rhys Evans is a British artificial intelligence researcher who works on AI alignment and machine learning safety. He founded Truthful AI, a research group based in Berkeley, California, and is an affiliate of the Center for Human Compatible AI (CHAI) at the University of California, Berkeley. His research addresses AI truthfulness, emergent behaviors in large language models, and the alignment of AI systems with human values. == Education == Evans earned a Bachelor of Arts in philosophy and mathematics from Columbia University in 2008 and a PhD in philosophy from the Massachusetts Institute of Technology in 2015. His doctoral research focused on Bayesian computational models of human preferences and decision-making. == Career == After completing his doctorate, Evans held positions at the Future of Humanity Institute (FHI) at the University of Oxford, first as a postdoctoral research fellow and later as a research scientist. While at FHI, he co-authored a survey of machine learning researchers on timelines for human-level AI, published in the Journal of Artificial Intelligence Research. The survey was reported on by Newsweek, New Scientist, the BBC, and The Economist. He was also among the co-authors of a 2018 report on the potential for misuse of AI technologies, published by researchers at Oxford, Cambridge, and other institutions. Since 2022, Evans has been based in Berkeley, where he founded Truthful AI, a non-profit research group that studies AI truthfulness, deception, and emergent behaviors in large language models. == Research == Evans's early work examined challenges in inverse reinforcement learning when human behavior is irrational or biased, proposing methods for AI systems to infer preferences from imperfect human demonstrations. He co-developed TruthfulQA (2021), a benchmark that tests whether language models give truthful answers rather than repeating common misconceptions. Initial evaluations found that larger models were not more truthful, suggesting that scaling alone does not improve factual accuracy. The benchmark has since been used by AI developers to evaluate large language models. He also co-authored a paper proposing design and governance strategies for building AI systems that do not deceive or hallucinate. In 2023, Evans and collaborators described the "reversal curse", showing that language models trained on a fact in one direction (e.g. "A is B") often cannot answer the corresponding reverse query ("B is A"). His group also developed a benchmark for evaluating situational awareness in language models. In 2025, Evans and colleagues published a study in Nature on what they termed "emergent misalignment": fine-tuning a language model on a narrow task (writing insecure code) caused it to produce unrelated harmful outputs without explicit instruction to do so. Later that year, Evans and collaborators (including researchers at Anthropic) reported that hidden behavioral traits can transfer between language models through training data, even when those traits are not explicitly present in the data, a phenomenon they called "subliminal learning". == Public engagement == In November 2025, Evans delivered the Hinton Lectures, a keynote lecture series on AI safety co-founded by Geoffrey Hinton and the Global Risk Institute.
Non-photorealistic rendering
Non-photorealistic rendering (NPR) is an area of computer graphics that focuses on enabling a wide variety of expressive styles for digital art, in contrast to traditional computer graphics, which focuses on photorealism. NPR is inspired by other artistic modes such as painting, drawing, technical illustration, and animated cartoons. NPR has appeared in movies and video games in the form of cel-shaded animation (also known as "toon" shading) as well as in scientific visualization, architectural illustration and experimental animation. == History and criticism of the term == The term non-photorealistic rendering is believed to have been coined by the SIGGRAPH 1990 papers committee, who held a session entitled "Non Photo Realistic Rendering". The term has received some criticism: The term "photorealism" has different meanings for graphics researchers (see "photorealistic rendering") and artists. For artists—who are the target consumers of NPR techniques—it refers to a school of painting that focuses on reproducing the effect of a camera lens, with all the distortion and hyper-reflections that it creates. For graphics researchers, however, it refers to an image that is visually indistinguishable from reality. In fact, graphics researchers lump the kinds of visual distortions that are used by photorealist painters into "non-photorealism". Describing something by what it is not is problematic. Equivalent (made-up) comparisons might be "non-elephant biology" or "non-geometric mathematics". NPR researchers have stated that they expect the term will disappear eventually and be replaced by the now more general term "computer graphics", with "photorealistic graphics" being the term used to describe "traditional" computer graphics. Many techniques that are used to create 'non-photorealistic' images are not rendering techniques. They are modelling techniques, or post-processing techniques. While the latter are coming to be known as 'image-based rendering', sketch-based modelling techniques, cannot technically be included under this heading, which is very inconvenient for conference organisers. The first conference on non-photorealistic animation and rendering included a discussion of possible alternative names. Among those suggested were "expressive graphics", "artistic rendering", "non-realistic graphics", "art-based rendering", and "psychographics". All of these terms have been used in various research papers on the topic, but the "non-photorealistic" term seems to have nonetheless taken hold. The first technical meeting dedicated to NPR was the ACM-sponsored Symposium on Non-Photorealistic Rendering and Animation(NPAR) in 2000. NPAR is traditionally co-located with the Annecy Animated Film Festival, running on even numbered years. From 2007 onward, NPAR began to also run on odd-numbered years, co-located with ACM SIGGRAPH. == 3D == Three-dimensional NPR is the style that is most commonly seen in video games and movies. The output from this technique is almost always a 3D model that has been modified from the original input model to portray a new artistic style. In many cases, the geometry of the model is identical to the original geometry, and only the material applied to the surface is modified. With increased availability of programmable GPU's, shaders have allowed NPR effects to be applied to the rasterised image that is to be displayed to the screen. The majority of NPR techniques applied to 3D geometry are intended to make the scene appear two-dimensional. NPR techniques for 3D images include cel shading and Gooch shading. Many methods can be used to draw stylized outlines and strokes from 3D models, including occluding contours and Suggestive contours. For enhanced legibility, the most useful technical illustrations for technical communication are not necessarily photorealistic. Non-photorealistic renderings, such as exploded view diagrams, greatly assist in showing placement of parts in a complex system. Cartoon rendering, also called cel shading or toon shading, is a non-photorealistic rendering technique used to give 3D computer graphics a flat, cartoon-like appearance. Its defining feature is the use of distinct shading colors rather than smooth gradients, producing a look reminiscent of comic books or animated films. This technique is often used to blend 3D objects and environments with 2D hand-animated elements while maintaining a consistent look. Treasure Planet movie by Disney is an example of blending these techniques. == 2D == The input to a two dimensional NPR system is typically an image or video. The output is a typically an artistic rendering of that input imagery (for example in a watercolor, painterly or sketched style) although some 2D NPR serves non-artistic purposes e.g. data visualization. The artistic rendering of images and video (often referred to as image stylization) traditionally focused upon heuristic algorithms that seek to simulate the placement of brush strokes on a digital canvas. Arguably, the earliest example of 2D NPR is Paul Haeberli's 'Paint by Numbers' at SIGGRAPH 1990. This (and similar interactive techniques) provide the user with a canvas that they can "paint" on using the cursor — as the user paints, a stylized version of the image is revealed on the canvas. This is especially useful for people who want to simulate different sizes of brush strokes according to different areas of the image. Subsequently, basic image processing operations using gradient operators or statistical moments were used to automate this process and minimize user interaction in the late nineties (although artistic control remains with the user via setting parameters of the algorithms). This automation enabled practical application of 2D NPR to video, for the first time in the living paintings of the movie What Dreams May Come (1998). More sophisticated image abstractions techniques were developed in the early 2000s harnessing computer vision operators e.g. image salience, or segmentation operators to drive stroke placement. Around this time, machine learning began to influence image stylization algorithms notably image analogy that could learn to mimic the style of an existing artwork. The advent of deep learning has re-kindled activity in image stylization, notably with neural style transfer (NST) algorithms that can mimic a wide gamut of artistic styles from single visual examples. These algorithms underpin mobile apps capable of the same e.g. Prisma In addition to the above stylization methods, a related class of techniques in 2D NPR address the simulation of artistic media. These methods include simulating the diffusion of ink through different kinds of paper, and also of pigments through water for simulation of watercolor. == Artistic rendering == Artistic rendering is the application of visual art styles to rendering. For photorealistic rendering styles, the emphasis is on accurate reproduction of light-and-shadow and the surface properties of the depicted objects, composition, or other more generic qualities. When the emphasis is on unique interpretive rendering styles, visual information is interpreted by the artist and displayed accordingly using the chosen art medium and level of abstraction in abstract art. In computer graphics, interpretive rendering styles are known as non-photorealistic rendering styles, but may be used to simplify technical illustrations. Rendering styles that combine photorealism with non-photorealism are known as hyperrealistic rendering styles. == Notable films and games == This section lists some seminal uses of NPR techniques in films, games and software. See cel-shaded animation for a list of uses of toon-shading in games and movies.
Generatrix
In geometry, a generatrix () or describent is a point, curve or surface that, when moved along a given path, generates a new shape. The path directing the motion of the generatrix motion is called a directrix or dirigent. == Examples == A cone can be generated by moving a line (the generatrix) fixed at the future apex of the cone along a closed curve (the directrix); if that directrix is a circle perpendicular to the line connecting its center to the apex, the motion is rotation around a fixed axis and the resulting shape is a circular cone. The generatrix of a cylinder, a limiting case of a cone, is a line that is kept parallel to some axis.
Jordan Antiquities Database and Information System
The Jordan Antiquities Database and Information System (JADIS) was a computer database of antiquities in Jordan, the first of its kind in the Arab world. It was established by the Department of Antiquities in 1990, in cooperation with the American Center for Oriental Research in Amman and sponsored by the United States Agency for International Development. JADIS was in use until 2002, when it was superseded by a new system, MEGA-J. Over 10,841 antiquities were registered in the database. An introduction and printed summary of the database was published by the Department of Antiquities in 1994, edited by Gaetano Palumbo.
Actor-critic algorithm
The actor-critic algorithm (AC) is a family of reinforcement learning (RL) algorithms that combine policy-based RL algorithms such as policy gradient methods, and value-based RL algorithms such as value iteration, Q-learning, SARSA, and TD learning. An AC algorithm consists of two main components: an "actor" that determines which actions to take according to a policy function, and a "critic" that evaluates those actions according to a value function. Some AC algorithms are on-policy, some are off-policy. Some apply to either continuous or discrete action spaces. Some work in both cases. == Overview == The actor-critic methods can be understood as an improvement over pure policy gradient methods like REINFORCE via introducing a baseline. === Actor === The actor uses a policy function π ( a | s ) {\displaystyle \pi (a|s)} , while the critic estimates either the value function V ( s ) {\displaystyle V(s)} , the action-value Q-function Q ( s , a ) , {\displaystyle Q(s,a),} the advantage function A ( s , a ) {\displaystyle A(s,a)} , or any combination thereof. The actor is a parameterized function π θ {\displaystyle \pi _{\theta }} , where θ {\displaystyle \theta } are the parameters of the actor. The actor takes as argument the state of the environment s {\displaystyle s} and produces a probability distribution π θ ( ⋅ | s ) {\displaystyle \pi _{\theta }(\cdot |s)} . If the action space is discrete, then ∑ a π θ ( a | s ) = 1 {\displaystyle \sum _{a}\pi _{\theta }(a|s)=1} . If the action space is continuous, then ∫ a π θ ( a | s ) d a = 1 {\displaystyle \int _{a}\pi _{\theta }(a|s)da=1} . The goal of policy optimization is to improve the actor. That is, to find some θ {\displaystyle \theta } that maximizes the expected episodic reward J ( θ ) {\displaystyle J(\theta )} : J ( θ ) = E π θ [ ∑ t = 0 T γ t r t ] {\displaystyle J(\theta )=\mathbb {E} _{\pi _{\theta }}\left[\sum _{t=0}^{T}\gamma ^{t}r_{t}\right]} where γ {\displaystyle \gamma } is the discount factor, r t {\displaystyle r_{t}} is the reward at step t {\displaystyle t} , and T {\displaystyle T} is the time-horizon (which can be infinite). The goal of policy gradient method is to optimize J ( θ ) {\displaystyle J(\theta )} by gradient ascent on the policy gradient ∇ J ( θ ) {\displaystyle \nabla J(\theta )} . As detailed on the policy gradient method page, there are many unbiased estimators of the policy gradient: ∇ θ J ( θ ) = E π θ [ ∑ 0 ≤ j ≤ T ∇ θ ln π θ ( A j | S j ) ⋅ Ψ j | S 0 = s 0 ] {\displaystyle \nabla _{\theta }J(\theta )=\mathbb {E} _{\pi _{\theta }}\left[\sum _{0\leq j\leq T}\nabla _{\theta }\ln \pi _{\theta }(A_{j}|S_{j})\cdot \Psi _{j}{\Big |}S_{0}=s_{0}\right]} where Ψ j {\textstyle \Psi _{j}} is a linear sum of the following: ∑ 0 ≤ i ≤ T ( γ i R i ) {\textstyle \sum _{0\leq i\leq T}(\gamma ^{i}R_{i})} . γ j ∑ j ≤ i ≤ T ( γ i − j R i ) {\textstyle \gamma ^{j}\sum _{j\leq i\leq T}(\gamma ^{i-j}R_{i})} : the REINFORCE algorithm. γ j ∑ j ≤ i ≤ T ( γ i − j R i ) − b ( S j ) {\textstyle \gamma ^{j}\sum _{j\leq i\leq T}(\gamma ^{i-j}R_{i})-b(S_{j})} : the REINFORCE with baseline algorithm. Here b {\displaystyle b} is an arbitrary function. γ j ( R j + γ V π θ ( S j + 1 ) − V π θ ( S j ) ) {\textstyle \gamma ^{j}\left(R_{j}+\gamma V^{\pi _{\theta }}(S_{j+1})-V^{\pi _{\theta }}(S_{j})\right)} : TD(1) learning. γ j Q π θ ( S j , A j ) {\textstyle \gamma ^{j}Q^{\pi _{\theta }}(S_{j},A_{j})} . γ j A π θ ( S j , A j ) {\textstyle \gamma ^{j}A^{\pi _{\theta }}(S_{j},A_{j})} : Advantage Actor-Critic (A2C). γ j ( R j + γ R j + 1 + γ 2 V π θ ( S j + 2 ) − V π θ ( S j ) ) {\textstyle \gamma ^{j}\left(R_{j}+\gamma R_{j+1}+\gamma ^{2}V^{\pi _{\theta }}(S_{j+2})-V^{\pi _{\theta }}(S_{j})\right)} : TD(2) learning. γ j ( ∑ k = 0 n − 1 γ k R j + k + γ n V π θ ( S j + n ) − V π θ ( S j ) ) {\textstyle \gamma ^{j}\left(\sum _{k=0}^{n-1}\gamma ^{k}R_{j+k}+\gamma ^{n}V^{\pi _{\theta }}(S_{j+n})-V^{\pi _{\theta }}(S_{j})\right)} : TD(n) learning. γ j ∑ n = 1 ∞ λ n − 1 1 − λ ⋅ ( ∑ k = 0 n − 1 γ k R j + k + γ n V π θ ( S j + n ) − V π θ ( S j ) ) {\textstyle \gamma ^{j}\sum _{n=1}^{\infty }{\frac {\lambda ^{n-1}}{1-\lambda }}\cdot \left(\sum _{k=0}^{n-1}\gamma ^{k}R_{j+k}+\gamma ^{n}V^{\pi _{\theta }}(S_{j+n})-V^{\pi _{\theta }}(S_{j})\right)} : TD(λ) learning, also known as GAE (generalized advantage estimate). This is obtained by an exponentially decaying sum of the TD(n) learning terms. === Critic === In the unbiased estimators given above, certain functions such as V π θ , Q π θ , A π θ {\displaystyle V^{\pi _{\theta }},Q^{\pi _{\theta }},A^{\pi _{\theta }}} appear. These are approximated by the critic. Since these functions all depend on the actor, the critic must learn alongside the actor. The critic is learned by value-based RL algorithms. For example, if the critic is estimating the state-value function V π θ ( s ) {\displaystyle V^{\pi _{\theta }}(s)} , then it can be learned by any value function approximation method. Let the critic be a function approximator V ϕ ( s ) {\displaystyle V_{\phi }(s)} with parameters ϕ {\displaystyle \phi } . The simplest example is TD(1) learning, which trains the critic to minimize the TD(1) error: δ i = R i + γ V ϕ ( S i + 1 ) − V ϕ ( S i ) {\displaystyle \delta _{i}=R_{i}+\gamma V_{\phi }(S_{i+1})-V_{\phi }(S_{i})} The critic parameters are updated by gradient descent on the squared TD error: ϕ ← ϕ − α ∇ ϕ ( δ i ) 2 = ϕ + α δ i ∇ ϕ V ϕ ( S i ) {\displaystyle \phi \leftarrow \phi -\alpha \nabla _{\phi }(\delta _{i})^{2}=\phi +\alpha \delta _{i}\nabla _{\phi }V_{\phi }(S_{i})} where α {\displaystyle \alpha } is the learning rate. Note that the gradient is taken with respect to the ϕ {\displaystyle \phi } in V ϕ ( S i ) {\displaystyle V_{\phi }(S_{i})} only, since the ϕ {\displaystyle \phi } in γ V ϕ ( S i + 1 ) {\displaystyle \gamma V_{\phi }(S_{i+1})} constitutes a moving target, and the gradient is not taken with respect to that. This is a common source of error in implementations that use automatic differentiation, and requires "stopping the gradient" at that point. Similarly, if the critic is estimating the action-value function Q π θ {\displaystyle Q^{\pi _{\theta }}} , then it can be learned by Q-learning or SARSA. In SARSA, the critic maintains an estimate of the Q-function, parameterized by ϕ {\displaystyle \phi } , denoted as Q ϕ ( s , a ) {\displaystyle Q_{\phi }(s,a)} . The temporal difference error is then calculated as δ i = R i + γ Q θ ( S i + 1 , A i + 1 ) − Q θ ( S i , A i ) {\displaystyle \delta _{i}=R_{i}+\gamma Q_{\theta }(S_{i+1},A_{i+1})-Q_{\theta }(S_{i},A_{i})} . The critic is then updated by θ ← θ + α δ i ∇ θ Q θ ( S i , A i ) {\displaystyle \theta \leftarrow \theta +\alpha \delta _{i}\nabla _{\theta }Q_{\theta }(S_{i},A_{i})} The advantage critic can be trained by training both a Q-function Q ϕ ( s , a ) {\displaystyle Q_{\phi }(s,a)} and a state-value function V ϕ ( s ) {\displaystyle V_{\phi }(s)} , then let A ϕ ( s , a ) = Q ϕ ( s , a ) − V ϕ ( s ) {\displaystyle A_{\phi }(s,a)=Q_{\phi }(s,a)-V_{\phi }(s)} . Although, it is more common to train just a state-value function V ϕ ( s ) {\displaystyle V_{\phi }(s)} , then estimate the advantage by A ϕ ( S i , A i ) ≈ ∑ j ∈ 0 : n − 1 γ j R i + j + γ n V ϕ ( S i + n ) − V ϕ ( S i ) {\displaystyle A_{\phi }(S_{i},A_{i})\approx \sum _{j\in 0:n-1}\gamma ^{j}R_{i+j}+\gamma ^{n}V_{\phi }(S_{i+n})-V_{\phi }(S_{i})} Here, n {\displaystyle n} is a positive integer. The higher n {\displaystyle n} is, the more lower is the bias in the advantage estimation, but at the price of higher variance. The Generalized Advantage Estimation (GAE) introduces a hyperparameter λ {\displaystyle \lambda } that smoothly interpolates between Monte Carlo returns ( λ = 1 {\displaystyle \lambda =1} , high variance, no bias) and 1-step TD learning ( λ = 0 {\displaystyle \lambda =0} , low variance, high bias). This hyperparameter can be adjusted to pick the optimal bias-variance trade-off in advantage estimation. It uses an exponentially decaying average of n-step returns with λ {\displaystyle \lambda } being the decay strength. == Variants == Asynchronous Advantage Actor-Critic (A3C): Parallel and asynchronous version of A2C. Soft Actor-Critic (SAC): Incorporates entropy maximization for improved exploration. Deep Deterministic Policy Gradient (DDPG): Specialized for continuous action spaces.
Himmat (app)
Himmat is a women's safety mobile application of Delhi Police. It was launched by Home Minister Rajnath Singh on 1 January 2015. The app is freely available for Android mobile phones and can be downloaded from Delhi Police website. Delhi Police plans to launch app for other platforms in future. Low registrations and other problems resulted in a parliamentary panel calling the app a failure in 2018. Himmat has gone on to be called as one of India's best safety apps for women.