“Texas Holdem Edge” educates Texas Holdem Poker enthusiasts to play better through tracking existing games or through playing various scenarios. Gain better decision-making skills with real-time insights and compare various circumstances through hypothesizing and hindsight review. Improve your game!
Past: Hindsight review
Real-time: Games insights as you play
Future: Hypothesize various scenarios
Who is this app for?
Texas Holdem Poker Enthusiasts: a virtual tracking assistant to help evaluate your game situations (online or in person) precisely and quickly, thus making more informed betting decisions while improving game-play skills on-the-fly.
Texas Holdem Poker Novices: teach players the intricacies of the Texas Holdem decision-making process without the need for playing a tremendous number of games and learning terminology, game-flow and decision-making consequences on-the-fly.
Reviewed at Gameskeys.net
Check out our recent review at Gameskeys.net as top game to play of the month for September 2020!
Features and Benefits
How is Texas Holdem Edge going to make you a better player? Check out all the great features you will have access to as you track games!
Assigning of Dealer Button (10 players shown)
Help with Decision-Making
Game Insights
Player Table Analysis
Simulate and track games to examine how gameplay was affected through:
Various number of starting players
Different dealer button placements
Opponents folding
Betting round transitions
Showdown preparedness
Hand Rank
Help with Decision-Making
Game Insights
Hand Rank Analysis - See how your dealt hand ranks, how your win chance changes with differing # of opponents, and examine your best hand chances throughout the game.
Win Chance
Best Hand
Your Odds/Medians
Help with Decision-Making
Game Insights
Card Texture Analysis - Examine your odds of various expected hands vs opponents, (including median hands), and your chances of having a killer hand or a dead hand throughout the game.
Killer Hand
Dead Hand
Search Possible Opponent Hands (Hand Rank Shown)
Hypothesizing
Explore various what-if scenarios including:
"What if my opponnent is holding...Ace King Suited?"
"What if other players fold?"
"How does my hand rank & chances change across rounds?"
You can go back in time or hypothesize the future!
Across # of Opponents
(Win Chance Shown)
Across Betting Rounds
(Best Hand Chance Shown)
Payout Games
Game Analysis and Review
Game Summary
Payout Games. Explore round-by-round summary including where particular players fold and their plausible losses
Notice when opponents fold based on table position (ie in relation to Dealer Button).
Which round to other players typically fold.
Which round does the winning player typically win in.
Showdown Games
Game Analysis and Review
Showdown Summary
Showdown Games. Access overall game summary for opponent player hindsight and game-flow chances with graphical interaction.
Access round detail summaries with expected hands and outs for each player. Chances and Final Hands are also included.
Expected Hands
(Summary)
Outs
(Particular Player Shown)
Game Review (Playback shown on Hole)
Game Analysis and Review
Game Review and Comparisons
Go forward and back throughout a game's timeline to see how various factors affect the outcome.
See how:
Folding occurrences change outcomes.
Differing hole cards affect outcomes.
Different community cards affect outcomes.
Why is Texas Holdem Edge unique?
The App does not require opponents to play against you as most apps require. This allows a user to explore how your decision to stay in or fold in a game impacts whether you win or lose. This new approach also allows a player to stop and think and evaluate their situation more clearly and not under pressure. A player can now deep dive to understand all aspects of game situations (changing dealt and community hands, number of players), and to go forward and backward in time to learn more.
Poker enthusiasts know that one can conscientiously track another players betting decisions over time and understand the leverage their holdings and pot commitments have on others at the table. However, “Texas Holdem Edge” will give you a better and more complete understanding of hand rank, card texture, player table position, and current betting round with number of opponents implications. When this knowledge is learned, and ingrained, will join the best players who grind out games and better counter the behavior of other players.
What it does...
The “Texas Holdem Edge” program is devised to:
educate you on the intricacies of the game
expand your understanding of the progression a player should take in making more informed betting decisions.
What it does not...
“Texas Holdem Edge” is not concerned with the individual chips placed in the pot. This is to simplify the game and provide a broader, more complete game theory perspective,
It is more focused on:
the overall process of staying in or getting out of a hand at the proper points in a game
using your leverage properly to maximize wins and minimize losses.
Ready to Improve Your Game?
Check back soon to download on the Apple iTunes App Store!
Interactive Aptitude, LLC is interested in partnering with universities, contracting with interested industry partners, and working with government agencies to further combat problems in climate change, national defense, and any other challenging problems. Thank you for visiting our website, we specialize in
Rapid prototype development to demonstrate a complex interactive concept
Algorithm development on solving your challenge problem using a variety of tools
Integrating machine learning algorithms into your product development
AI Solutions for DoD Operations
We provide comprehensive software consulting services to discover & implement all-domain DoD solutions for streamlining workflows, multi-sensor data fusion, wargaming simulation, and decentralized BMC3.
Artificial Intelligence algorithms need to be tailored and optimized to fit the problem. We handle the integration with user interaction and complementary visualization of results.
Data Analysis
Data analysis is the use of statistical tools, AI algorithms and a contextual framework to make sense and leverage information for a specific purpose. We use a variety of analytical tools and have the ability to emerge intelligent decision-making on-the-fly with interaction and feedback.
iOS App Integration
App Integration requires simultaneous fulfillment of both the goals of the App founder and the user experience to create a marketable product. We handle App development with embedded AI techniques from the early design phases to in-store distribution.
AI Orchestration
Artificial Intelligence learns from data, goals and environment interaction to improve outcomes. We design, architect, and build AI orchestrated environments that fulfill your business requirements.
iOS App Products
Best Hand Challenge Poker App
Choose the best poker hand and see if you are correct! (Summer 2022)
Texas Holdem Edge App
Track, analyze and improve your Texas Holdem Poker game performance! (Winter 2018)
The success of your project comes down to a quality process!
Biography
James Vaccaro started Interactive Aptitude (IA), LLC nearly five years ago. His research and development areas of interest include scalable machine learning technologies, autonomous interactive systems, and adaptive multi-agent systems that can plan as well as learn. His Interactive Aptitude, LLC company includes both contract work and in-house product development and distribution. In contract work, he has developed several novel algorithms in multi-agent autonomous planning, diversity in plan selection, multi-objective optimization and real-time simulation for urban and regional environments to test and evaluate planning technologies. In internal IA work, he has developed two mobile applications (in Apple Store) that emphasize his unique talents of integrating mathematical models into pragmatic user interactive products that train users in Texas Hold’em circumstantial play with integrated online help for understanding the context of the situation. Prior to starting Interactive Aptitude, LLC, he worked for several start up companies in algorithms, software architectural design and product implementation in color blind aided fashion design, security trust systems and pairing real estate agents to clients via online textual communications analysis. He holds two patents from related work in these areas. Early in his career, he worked on several Artificial Intelligent efforts in the US Air Force on neural-biologically plausible systems on how humans sense the world and included university cooperative projects in auditory, aesthetic, olfactory, and cognitive neural systems. Dr. Vaccaro received B.S. in Electrical and Computer Engineering (ECE) at Clarkson University, his M.S. in ECE at Syracuse University and his Ph.D. at the University of California, San Diego.
Honors and Awards
ACK Medal for contribution on ACK program (2022)
TAA Medal for contribution on TAA program (2021)
Urban Domain AI Prototype Application (2019)
Placed first app for my company in the Apple Store (2019)
First app in the app store - Color Butler (2018)
Color Blind wardrobe Assistant Architecture (Patented) (2017)
Started my own business (2017)
Real Estate Social Media Assistant Architecture (Patented) (2014)
IEEE Technical Program Chair for Computational Intelligence and Games Conference (2009-12)
IEEE Computational Intelligence Chair (2008-11)
Lockheed Martin Grand Challenge Winner (2007)
Best Paper Presentation (WCCI06 Conference) 2006
Windows on Europe (ONERA/CERT) (1998)
Windows on Europe (University of Bochum) (1993)
Windows on the United States (UC Berkeley) (1992)
Principle Investigator of Computing with Oscillators (1992)
Publications
Victor Bajenaru, James Vaccaro, Mitchell Colby, Brett Benyo, "Comprehensive Top-K Recommender System for Command and Control, using Novel Evaluation and Optimization Algorithms", SPIE 2022 Defense and Commercial Sensing Conference, April 2022.
J. Vaccaro, “Dynamic Planning in a Real-Time Multi-Player Strategy Game,” AFRL Visiting Professor Final Report, December 2011.
J. Vaccaro, “Autonomous Dynamic Planning and Execution for Very Large Partially Observable and Stochastic Environments,” Computer Engineering Ph.D. Dissertation, June 2010.
J. Vaccaro, C. Guest, “Modelling, Simulating and Autonomous Planning for Urban Search and Rescue,” Modelling, Simulation and Optimization, Book Chapter, In-Tech Publishing, February 2010.
J. Vaccaro, C. Guest, “Modeling Social Influence via Combined Centralized and Distributed Planning Control,” MODSIM World Conference and Expo, Virginia Beach, VA, October 2009.
J. Vaccaro, C. Guest, “Modeling Urban Terrain for Simulating Search and Rescue Operations to Train Planners,” IASTED Applied Modeling and Simulation Conference, Corfu, Greece, June 2008.
J. Vaccaro, C. Guest, “Automated Dynamic Planning and Execution for a Partially Observable Game Model: Tsunami City Search and Rescue,” IEEE World Congress on Computational Intelligence (WCCI’08), Hong Kong, China, June 2008.
J. Vaccaro, C. Guest, “Learning Multiple Search, Utility and Goal Parameters for the Game RISK,” IEEE Congress on Evolutionary Computation, Vancouver, Canada, July 2006, pp. 4351-4358.
J. Vaccaro, C. Guest, “Planning an Endgame Move Set for the Game RISK: A Comparison of Search Algorithms,” IEEE Transactions on Evolutionary Computation, Vol. 9, No. 6, December 2005, pp. 641-652.
J. Vaccaro, C. Guest, “Evolutionary Bayesian Network Dynamic Planner for Game RISK,” Lecture Notes in Computer Science: Applications of Evolutionary Computation, EvoSTOC Proceedings, Coimbra, Portugal, April 2004, pp. 549-560.
J. Vaccaro, C. Guest, D. Ross. “Evolutionary Programming for Goal-Driven Dynamic Planning,” SPIE’s 16th Aerosense Symposium, Orlando, FL, April 2002.
J. Vaccaro, C. Guest, P. Yaworsky, S. Alexander. “Comparison of Recurrent Neural Networks with Evolutionary Learning, Fuzzy-Logic, and Rule-Based Approaches in a Goal-Driven Application.” 3rd International Conference on Dynamic Neural Networks (DYNN), Bielefeld, Germany, November 2000.
J. Vaccaro, P. Yaworsky. “Real-Time Modeling of Primitive Environments through Wavelet Sensors and Hebbian Learning.” SPIE's 13th Annual International Symposium on Aerospace/Defense Sensing, Simulation and Controls, Orlando, April 1999.
J. Vaccaro, D. Gourion, M. Samuelides, S. Thorpe. “Rank-Based Hebbian Learning in a Multi-Layered Neural Network.” International Conference on Neural Networks & Virtual Intelligence (DYNN & VI), Stockholm, Sweden, June 1998.
J. Vaccaro, P. Yaworsky. “A Soft-Computing Method for Spatio-Temporal Data Representation and Processing.” International Conference on Informatics and Controls (ICI&C), St. Petersburg, Russia, June 1997.
P. Yaworsky, J. Vaccaro. “Neural Networks, Reliability and Data Analysis.” In-house technical report, RL-TR 93-5, January 1993.
J. Vaccaro. “Computing with Oscillators - Normal Form Projection Network for an Associative Memory.” Simtech Conference, Houston, Fall 1992.
J. Vaccaro. “A Statistical Neural Network.” Master’s Thesis Project, Syracuse University, July 1991.
Portfolio
We provide comprehensive software consulting services in rapid prototype development to demonstrate a complex interactive concept, in algorithm development on solving your challenge problem using a variety of tools, and in integrating machine learning algorithms into your product development.
Examples of work...
Check out below for detailed slides of projects and portfolio pieces in the data analysis, AI and app integration efforts by Interactive Aptitude.
RISK Game: Example RISK plan w/ 14 battle tasks
RISK Game
Problem Domain: Turn-Based Interactive Planning under Uncertain Outcomes
Customer: Self (University of California, San Diego Ph.D.)
Software: Matlab
Technologies Explored: Comparison of Bayesian Network Tree Search Algorithms with Replanning Capability as player’s turn unfolds: Depth First, Breadth First, Simulated Annealing, Multi-Objective Evolutionary Algorithm with Diversity and Risk Aversion compared
Lessons Learned: The Multi-Objective Evolutionary Algorithm with Diversity and Risk Aversion was by far the most adaptive to beginning, middle and end game strategies
Products: 3 Publications below and a Matlab Prototype (See example Image)
J. Vaccaro, C. Guest, “Learning Multiple Search, Utility and Goal Parameters for the Game RISK,” IEEE Congress on Evolutionary Computation, Vancouver, Canada, July 2006, pp. 4351-4358.
J. Vaccaro, C. Guest, “Planning an Endgame Move Set for the Game RISK: A Comparison of Search Algorithms,” IEEE Transactions on Evolutionary Computation, Vol. 9, No. 6, December 2005, pp. 641-652.
J. Vaccaro, C. Guest, “Evolutionary Bayesian Network Dynamic Planner for Game RISK,” Lecture Notes in Computer Science: Applications of Evolutionary Computation, EvoSTOC Proceedings, Coimbra, Portugal, April, 2004, pp. 549-560.
Search and Rescue Operation.
Urban Search and Rescue of Tsunami Event
Problem Domain: Real-Time Simulation of Tsunami Rescue Event with limited resources, multi-type agents, partially observable environment, many buildings to search, and constrained access and people to rescue
Customer: Self (University of California, San Diego Ph.D.)
Software: Matlab
Technologies Explored: Delaunay Triangular Land, Sea and Sky representation, Dynamic Planning with a Markov Decision Process Tree Representation, Evolutionary Search with Risk Aversion, and Beta Distribution Learning of Relevant Features
Lessons Learned: Approach was able to learn best set of agents, communication frequency to update model, and relevant feature value function to reduce replanning and ensure near optimal evacuation strategy
Products: 3 Publications below and a Matlab Prototype (See example Image)
J. Vaccaro, C. Guest, “Modelling, Simulating and Autonomous Planning for Urban Search and Rescue,” Modelling, Simulation and Optimization, Chapter 25, In-Tech Publishing, February 2010.
J. Vaccaro, C. Guest, “Modeling Urban Terrain for Simulating Search and Rescue Operations to Train Planners,” IASTED Applied Modeling and Simulation Conference, in press, Corfu, Greece, June 2008.
J. Vaccaro, C. Guest, “Automated Dynamic Planning and Execution for a Partially Observable Game Model: Tsunami City Search and Rescue,” IEEE World Congress on Computational Intelligence (WCCI’08), in press, Hong Kong, China, June 2008.
Color Blind Fashion Application
Problem Domain: Human interactive mobile application to help color blind get dressed for the day. Uses the camera and photo library to import clothes and color, with autonomous detection of color, user selection of the appropriate wireframe and an interface to create an outfit from a stored and interactive closet.
Customer: Color Butler Inc.
Software: Swift
Technologies Explored: Multi-Level Object Oriented Programming with the interaction of Several Clothes Representations, Color Identification Neural Network, and Outfit Matching Rule-Based System
Lessons Learned: Full Software Product End-to-End Development and Distribution, Rank-Based analysis of several clothes Features: color, designing wireframe type and layered combinations, and built-in interface with tutorial and several user-interfaces. Prototype was fielded in the Apple Store. Given more capital the application would have tremendous potential.
Products: Swift Application in Apple Store (See screenshots and built-in tutorial demo). A patent has been published.
Texas Hold’em Edge
Problem Domain: The problem solved in this application is getting Texas Hold’em Users instantaneously probability and statistics about their hand given the number of players, the cards they hold, and the cards on the table. There are approximately 1 billion combinations of probability density functions of a user’s hand in comparison to their opponents.
Customer: Interactive Aptitude LLC
Software: Objective C
Technologies Explored: Application uses Bayesian Networks with Rank-Based Analysis to determine, win, tie, lose probability, hand rank, best hand probability, dead hand and winning hand certainty, and probability hindsight based on looking back at cards dealt. In addition, for hand showdowns, all outs are fully predicted for all players.
Lessons Learned: When building an application from the ground up, all billion combinations can be smartly coded for quick access. Application was very functionally based but lacked the Marketing push that kept it from generating a lot of revenue. Having an app that required an initial purchase is hard to sell given many similar apps that lacked the completeness of Texas Hold’em Edge. Different marketing approaches are being studied.
Products: Texas Hold’em Edge App is in the Apple Store.
Problem Domain: This application uses a subset of the calculation engine built in Texas Hold’em Edge. This app concentrates on teaching a player to understand their chances in a game and rank of their hand based on phase of a game and number of opponents. Also, players can track their improvement on different game circumstances and be better prepared for tournament play.
Customer: Interactive Aptitude LLC
Software: Objective C
Technologies Explored: New technologies explored here are in creating a statistaccly based feedback system to train players based on their speed, accuracy and streak of identifying the best hand given a sequence of hand challenges.
Lessons Learned: This application uses a different marketing strategy by presenting a free app with AdMob advertising. We are in the intial phases of understanding the impact of such an approach.
Products: Best Hand Challenge App will be in the Apple Store when advertising model is finished. Summer 2022.
Problem Domain: War torn cities have a mix of people going about their business and enemy combatants lurking in the crowd. The behavior on how they react to authority could possibly determine their allegiance. Using Partially Observable Markov Decision Processes (POMDP) along with the noise induced by nominal activity can we separate the combatants from the citizens?
Customer: Scientific Systems Company Incorporated
Software: Objective C
Technologies Explored: Using modeling and simulation, using raster ground representation and raytracing for line of sight, can we construct the city dynamics and some intruders to illustrate the behavior and POMDP technology that identifies friend from foe.
Lessons Learned: Integrated Monte Carlo behavior in both civilian and combatants to produce a large array of simulations to demonstrate the technology. System can also run at extreme real-time to capture a lot of data.
Products: The product was a demonstration of a real-time device planning of UAV resources for crowd control and targeting of enemy combatants. This was part of a DARPA project.
Problem Domain: Given real-world data, we would like to analyze the scene based on many points of view and timeline constraints. Interface needs to include lines of sight of all points of view. Interactive agents, whether human or unmanned have sensor capability limited by distance, facing direction, line-of-sight and distractive elements in their near field location.
Customer: Scientific Systems Company Incorporated
Software: Objective C
Technologies Explored: Ray tracing lines of sight, an adaptive timeline that links all time vectors of each character in the scene. A variable look into the scene movement given beginning, end and current time.
Lessons Learned: Creating a usable storytelling application help gain insight into new forms of scene presentation and can be useful on future projects when the scene gets complex.
Products: The product was a demonstration of possible scenarios given a real scene and collected data. This was part of a DARPA project.
Dog Handler Data Collection
Problem Domain: Rescue dogs have different behavior and communication protocols with their handlers. To learn the behaviors of both dogs and their handlers, an app needed to be built that allowed for integration of the map, an ability to draw both scent plumes and observed movement activity, while labeling the activity with a set of observables for training the best use of the handlers with the animals.
Customer: Scientific Systems Company Incorporated
Software: Swift
Technologies Explored: User interface had login and security protection along with the use of Apple Maps, a created overlay to add observed movements on the ground and the ability to place observables from a set of possible observations. Also, the ability to draw a plume and change any node or link based on position, observation and order.
Lessons Learned: Integration of several technologies working together including interactive Map, drawing a plume on the map, interactive planning of movement markers and managing multiple dogs and handlers with data storage and retrieval.
Products: The Dog Handler App was used by government officials using the TestFlight distribution on an iPad device.
Multi-Objective Search and Engagement Planning (Shared Resources Analysis)
Problem Domain: Given cloud coverage, a sortie assignment and a set of available assets, can we find the best combination of assets that meets the challenge based on priorities on time, cost, covertness and opportunity costs. Problem had both air and satellite resources and a set of missions from detect to engage a target.
Customer: Scientific Systems Company Incorporated
Software: Objective C
Technologies Explored: Multi-objective optimization, merging multiple agents on a given task, creating algorithms for calculating temporal costs, risks, and other metrics to formulate an overall multi-objective optimization calculation. Also, priorities can be changed real time to see the impact of which best asset combinations are best for a prescribed task.
Lessons Learned: Creating a real-time adaptive system gave insight into how to organize the calculation to account for both priority shifts and addressing combination of assets as a secondary process.
Products: The product was a real-time demonstration of choosing the best asset combinations based on a random sortie event. This was part of the DARPA ACK project.
Multi-Objective Search and Engagement Planning (Optimize Defensive Posture)
Problem Domain: As with many attacks, the enemy does not want you to know when and where they will strike. This problem was a demonstration of reactive behavior based on calculating the best defensive counterstrike capability while maintaining a level of vigilance by maintaining a defensive posture.
Customer: Scientific Systems Company Incorporated
Software: Objective C
Technologies Explored: A multi-objective approach was explored to determine a course of action that met several metrics, including collateral damage, timeliness, reachability, and defensibility to near time future strikes.
Lessons Learned: Speed of the target, placement of resources (reconnaissance and engagement), contingency planning and defensive posture all play a role in the success of long-term defensive.
Products: A demonstration application with many required algorithms was developed. Algorithms include moving target interception, weighted multi-objective optimization, and creating time and event plan compositions.
Diversity Planning over Multiple Domains
Problem Domain: When developing plans with multiple ways to response, can we develop an algorithm to order the options that are near or on the pareto front while having a diverse set of options near the top of the list.
Customer: Scientific Systems Company Incorporated
Software: Objective C, Java and Python
Technologies Explored: To measure nearness to the pareto front, a mesh was created that explored the proximity to that and provided a metric to visualize the distance among the options. Options were measured by each objective (e.g., timeliness, probability of success, etc.) and also by difference in domain, asset and actions involved. Using evolutionary computation and deep learning, we explored how to calculate the best set of options based on user’s preferences and distance metrics together.
Lessons Learned: Approach was deemed to be unique and well thought out. A publication was generated that explains the advantages of this approach.
Products: Prototype demonstration in Objective C and on an iPad, a Java implementation for delivered system and a python experimental model for developing the published paper below.
Victor Bajenaru, James Vaccaro, Mitchell Colby, Brett Benyo, "Comprehensive Top-K Recommender System for Command and Control, using Novel Evaluation and Optimization Algorithms", SPIE 2022 Defense and Commercial Sensing Conference, April 2022.
Real-Time Adversarial Planning (e.g. StarCraft)
Problem Domain: A game like StarCraft requires dynamic interactive gameplay as enemy units are discovered and engaged. A two-player game with multiple agent types is explored to determine if an interactive planning approach can create useful behavior that adapts to the environment and enemies encountered.
Customer: Interactive Aptitude LLC
Software: Swift
Technologies Explored: This project explores the use adaptive planning given a hierarchical framework, time and space sampling rate, a time horizon of planning and many more features to discover the relevant features required for adaptive planning behavior.
Lessons Learned: A Monte Carlo learning strategy was designed and could be used to train the planning behavior if given enough training data. With this adaptive approach, changing the characteristics of the agents immediately changed the strategy of the planners. Given future projections of friendly units and projected locations of enemy units, plans can form a cooperative behavior of intercepting the enemy at different points.
Products: Demonstration of the planning system is completed on an iPad device with two Battlecruiser units on one side and seven Viking Cruisers on the other.
James Vaccaro started Interactive Aptitude (IA), LLC nearly five years ago. His research and development areas of interest include scalable machine learning technologies, autonomous interactive systems, and adaptive multi-agent systems that can plan as well as learn. His Interactive Aptitude, LLC company includes both contract work and in-house product development and distribution. In contract work, he has developed several novel algorithms in multi-agent autonomous planning, diversity in plan selection, multi-objective optimization and real-time simulation for urban and regional environments to test and evaluate planning technologies. In internal IA work, he has developed two mobile applications (in Apple Store) that emphasize his unique talents of integrating mathematical models into pragmatic user interactive products that train users in Texas Hold’em circumstantial play with integrated online help for understanding the context of the situation. Prior to starting Interactive Aptitude, LLC, he worked for several start up companies in algorithms, software architectural design and product implementation in color blind aided fashion design, security trust systems and pairing real estate agents to clients via online textual communications analysis. He holds two patents from related work in these areas. Early in his career, he worked on several Artificial Intelligent efforts in the US Air Force on neural-biologically plausible systems on how humans sense the world and included university cooperative projects in auditory, aesthetic, olfactory, and cognitive neural systems. Dr. Vaccaro received B.S. in Electrical and Computer Engineering (ECE) at Clarkson University, his M.S. in ECE at Syracuse University and his Ph.D. at the University of California, San Diego.
