Daniel Shapiro - Academia.edu (original) (raw)
Papers by Daniel Shapiro
Engineering Applications of Artificial Intelligence, 1994
isle.org
Hierarchical reinforcement learning techniques operate on structured plans. Although structured r... more Hierarchical reinforcement learning techniques operate on structured plans. Although structured representations add expressive power to Markov Decision Processes (MDPs), current approaches impose constraints that force the associated convergence proofs to depend upon a subroutinestyle execution model that restricts adaptive response. We develop an alternate approach to convergent learning that employs hierarchical plans with an interruptible (reactive) execution model. We prove this format reduces to an MDP, and thus that we can implement any algorithm that converges on MDPs directly on reactive plans. We introduce one such algorithm, called Sharsha(0) (an acronym for state hierarchy, action, state hierarchy, action) that simultaneously finds the Q-values for subplans and the optimal hierarchical policy via an on-line exploration of a single, infinitely long execution sequence.
Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment
We have constructed a system that supports unscripted social interaction between a player and vir... more We have constructed a system that supports unscripted social interaction between a player and virtual characters, where the participants pursue internal agendas and respond to one another in real-time. Our emphasis on unscripted interaction means that the characters must accept dynamically generated performance requests, while our concern with social interaction implies that the characters must interleave performances with an attention to natural flow that encourages social engagement. We present initial work on a performance management mechanism that produces this interleaving. It initiates and suspends character performances by allocating animation resources to requests via a utility function representing aesthetic concerns. That function weighs extrinsic factors reflecting the purpose of taking an action against intrinsic ones that concern features of a given performance. We show, via multiple short videos, that the features are individually material to the aesthetic quality...
arXiv (Cornell University), Mar 27, 2013
Adaptive Agents and Multi-Agents Systems, May 4, 2015
International Conference on Software Engineering, Mar 26, 1984
This paper presents work in progress towards a program development and maintenance aid called the... more This paper presents work in progress towards a program development and maintenance aid called the Intelligent Program Editor (IPE), which applies artificial intelligence techniques to the task of manipulating and analyzing programs. The IPE is a knowledge based tool: it gains its power by explicitly representing textual, syntactic, and many of the semantic (meaning related) and pragmatic (application oriented) structures in programs. To demonstrate this approach, we implement a subset of this knowledge base, and a search mechanism called the Program Reference Language (PRL), which is able to locate portions of programs based on a description provided by a user.
To prepare for the problem of accidents in Space Station activities, the Extravehicular Activity ... more To prepare for the problem of accidents in Space Station activities, the Extravehicular Activity Retriever (EVAR) robot is being constructed, whose purpose is to retrieve astronauts and tools that float free of the Space Station. Advanced Decision Systems is at the beginning of a project to develop research software capable of guiding EVAR through the retrieval process. This involves addressing problems in machine vision, dexterous manipulation, real time construction of programs via speech input, and reactive execution of plans despite the mishaps and unexpected conditions that arise in uncontrolled domains. The problem analysis phase of this work is presented. An EVAR scenario is used to elucidate major domain and technical problems. An overview of the technical approach to prototyping an EVAR system is also presented.
AI Magazine, 2011
This issue of AI Magazine provides extended versions of several papers that were recently present... more This issue of AI Magazine provides extended versions of several papers that were recently presented at the Innovative Applications of Artificial Intelligence Conference (IAAI‐2010). We present three articles reflecting deployed applications of AI, one describing a unique, emerging application, plus an article based on the invited talk by Jay M. Tenenbaum, who was the 2010 Engelmore Award recipient.
This paper proposes an interactive debugging aid that exhibits a deep understanding of a narrow c... more This paper proposes an interactive debugging aid that exhibits a deep understanding of a narrow class of bugs. This system, called Sniffer, will be able to find and identify errors, and explain them in terms which are relevant to the programmer. Sniffer is knowledgeable about side-effects. It is capable of citing the data which was in effect at the time an error became manifest. The debugging knowledge in Sniffer is organized as a collection of independent experts which know about particular errors. The experts (sniffers) perform their function by applying a feature recognition process to the text for the program, and to the events which took place during the execution of the code. No deductive machinery is involved. The experts are supported by two systems; the cliche finder which identifies small portions of algorithms from a plan for the code, and the time rover which provides complete access to all program states that ever existed. Sniffer is embedded in a run-time debugging aid...
IEEE Transactions on Software Engineering, 1985
A research prototype software system for conceptual information retrieval has been developed. The... more A research prototype software system for conceptual information retrieval has been developed. The goal of the system, ca)led RUBRIC, is to provide more automated and relevant access to unformatted textual databases. The approach is to use production rules from artificial intelligence to define a hierarchy of retrieval subtopics, with fuzzy context expressions and specific word phrases at the bottom. RUBRIC allows the definition of detailed queries starting at a conceptual level, partial matching of a query and a document, selection of only the highest ranked documents for presentation to the user, and detailed explanation of how and why a particular document was selected. Initial experiments indicate that a RUBRIC rule set better matches human retrieval judgment than a standard Boolean keyword expression, given equal amounts of effort in defining each. The techniques presented may be useful in stand-alone retrieval systems, front-ends to existing information retrieval systems, or real-time document filtering and routing Index Terms-Artificial intelligence, evidential reasoning, expert systems, information retrieval.
Autonomous Agents & Multiagent Systems/International Conference on Autonomous Agents, 2004
In this paper we describe ICARUS, an integrated architecture for intelligent physical agents. The... more In this paper we describe ICARUS, an integrated architecture for intelligent physical agents. The framework supports long-term memories for hierarchical concepts and skills, along with mechanisms for recognizing concepts that hold in the environment, determining which skills are applicable, and selecting for execution the skill with the highest expected value. We illustrate these processes with examples from the domain of
isle.org
The paper abstract should begin in the left column, 0.* inches below the final address. The headi... more The paper abstract should begin in the left column, 0.* inches below the final address. The heading 'Abstract'should be centered, bold, and in** point type. The abstract body should use 10 point type, with a vertical spacing of** points, and should be indented ...
Cognitive Systems Research, 2009
In this paper, we present an approach to transfer that involves analogical mapping of symbols acr... more In this paper, we present an approach to transfer that involves analogical mapping of symbols across different domains. We relate this mechanism to ICARUS, a theory of the human cognitive architecture. Our system can transfer skills across domains hypothesizing maps between representations, improving performance in novel domains. Unlike previous approaches to analogical transfer, our method uses an explanatory analysis that compares how well a new domain theory explains previous solutions under different mapping hypotheses. We present experimental evidence that the new mechanism improves transfer over ICARUS' basic learning processes. Moreover, we argue that the same features which distinguish ICARUS from other architectures support representation mapping in a natural way and operate synergistically with it. These features enable our analogy system to translate a map among concepts into a map between skills, and to support transfer even if two domains are only partially analogous. We also discuss our system's relation to other work on analogy and outline directions for future research.
Developing autonomous agents for computer games is often a lengthy and expensive undertaking that... more Developing autonomous agents for computer games is often a lengthy and expensive undertaking that requires manual encoding of detailed and complex knowledge. In this paper we show how to acquire hierarchical skills for controlling a team of simulated football players by observing video of college football play. We then demonstrate the results in the Rush 2008 football simulator, showing that the learned skills have high fidelity with respect to the observed video and are robust to changes in the environment. Finally, we conclude with discussions of this work and of possible improvements.
2011 IEEE 24th International Conference on Micro Electro Mechanical Systems, 2011
s .................................................................................................. more s ....................................................................................................... 24 Author Index .................................................................................................. 40 Keyword Index ............................................................................................... 44
Computational Intelligence, 2007
IEEE Intelligent Systems, 2008
The European Commission's Information Society Technologies Advisory Group (Istag) introduced the ... more The European Commission's Information Society Technologies Advisory Group (Istag) introduced the concept of ambient intelligence. 1-3 Basically, AmI refers to a digital environment that proactively, but sensibly, supports people in their daily lives. 4 IEEE Intelligent Systems was one of the first publications to emphasize AmI's importance, with Nigel Shadbolt's editorial in the July/August 2003 issue. 5 Other concepts such as ubiquitous computing, pervasive computing, con text awareness, and embedded systems overlap with AmI, but there are distinctive differences. 6 The Istag reports define AmI at a concep tual level and identify important technologies for achieving it. In Ambient Intelligence: From Vision to Reality, Istag refers to these AmI components: smart materials, microelectromechanical systems and sensor technologies, embedded systems, ubiq uitous communications, I/O device technology, and adaptive software. 3 The report also mentions these intelligence components: media management and handling, natural interaction, computational intel ligence, context awareness, and emotional com puting. In our opinion, achieving AmI will require borrowing much more from artificial intelligence.
Engineering Applications of Artificial Intelligence, 1994
isle.org
Hierarchical reinforcement learning techniques operate on structured plans. Although structured r... more Hierarchical reinforcement learning techniques operate on structured plans. Although structured representations add expressive power to Markov Decision Processes (MDPs), current approaches impose constraints that force the associated convergence proofs to depend upon a subroutinestyle execution model that restricts adaptive response. We develop an alternate approach to convergent learning that employs hierarchical plans with an interruptible (reactive) execution model. We prove this format reduces to an MDP, and thus that we can implement any algorithm that converges on MDPs directly on reactive plans. We introduce one such algorithm, called Sharsha(0) (an acronym for state hierarchy, action, state hierarchy, action) that simultaneously finds the Q-values for subplans and the optimal hierarchical policy via an on-line exploration of a single, infinitely long execution sequence.
Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment
We have constructed a system that supports unscripted social interaction between a player and vir... more We have constructed a system that supports unscripted social interaction between a player and virtual characters, where the participants pursue internal agendas and respond to one another in real-time. Our emphasis on unscripted interaction means that the characters must accept dynamically generated performance requests, while our concern with social interaction implies that the characters must interleave performances with an attention to natural flow that encourages social engagement. We present initial work on a performance management mechanism that produces this interleaving. It initiates and suspends character performances by allocating animation resources to requests via a utility function representing aesthetic concerns. That function weighs extrinsic factors reflecting the purpose of taking an action against intrinsic ones that concern features of a given performance. We show, via multiple short videos, that the features are individually material to the aesthetic quality...
arXiv (Cornell University), Mar 27, 2013
Adaptive Agents and Multi-Agents Systems, May 4, 2015
International Conference on Software Engineering, Mar 26, 1984
This paper presents work in progress towards a program development and maintenance aid called the... more This paper presents work in progress towards a program development and maintenance aid called the Intelligent Program Editor (IPE), which applies artificial intelligence techniques to the task of manipulating and analyzing programs. The IPE is a knowledge based tool: it gains its power by explicitly representing textual, syntactic, and many of the semantic (meaning related) and pragmatic (application oriented) structures in programs. To demonstrate this approach, we implement a subset of this knowledge base, and a search mechanism called the Program Reference Language (PRL), which is able to locate portions of programs based on a description provided by a user.
To prepare for the problem of accidents in Space Station activities, the Extravehicular Activity ... more To prepare for the problem of accidents in Space Station activities, the Extravehicular Activity Retriever (EVAR) robot is being constructed, whose purpose is to retrieve astronauts and tools that float free of the Space Station. Advanced Decision Systems is at the beginning of a project to develop research software capable of guiding EVAR through the retrieval process. This involves addressing problems in machine vision, dexterous manipulation, real time construction of programs via speech input, and reactive execution of plans despite the mishaps and unexpected conditions that arise in uncontrolled domains. The problem analysis phase of this work is presented. An EVAR scenario is used to elucidate major domain and technical problems. An overview of the technical approach to prototyping an EVAR system is also presented.
AI Magazine, 2011
This issue of AI Magazine provides extended versions of several papers that were recently present... more This issue of AI Magazine provides extended versions of several papers that were recently presented at the Innovative Applications of Artificial Intelligence Conference (IAAI‐2010). We present three articles reflecting deployed applications of AI, one describing a unique, emerging application, plus an article based on the invited talk by Jay M. Tenenbaum, who was the 2010 Engelmore Award recipient.
This paper proposes an interactive debugging aid that exhibits a deep understanding of a narrow c... more This paper proposes an interactive debugging aid that exhibits a deep understanding of a narrow class of bugs. This system, called Sniffer, will be able to find and identify errors, and explain them in terms which are relevant to the programmer. Sniffer is knowledgeable about side-effects. It is capable of citing the data which was in effect at the time an error became manifest. The debugging knowledge in Sniffer is organized as a collection of independent experts which know about particular errors. The experts (sniffers) perform their function by applying a feature recognition process to the text for the program, and to the events which took place during the execution of the code. No deductive machinery is involved. The experts are supported by two systems; the cliche finder which identifies small portions of algorithms from a plan for the code, and the time rover which provides complete access to all program states that ever existed. Sniffer is embedded in a run-time debugging aid...
IEEE Transactions on Software Engineering, 1985
A research prototype software system for conceptual information retrieval has been developed. The... more A research prototype software system for conceptual information retrieval has been developed. The goal of the system, ca)led RUBRIC, is to provide more automated and relevant access to unformatted textual databases. The approach is to use production rules from artificial intelligence to define a hierarchy of retrieval subtopics, with fuzzy context expressions and specific word phrases at the bottom. RUBRIC allows the definition of detailed queries starting at a conceptual level, partial matching of a query and a document, selection of only the highest ranked documents for presentation to the user, and detailed explanation of how and why a particular document was selected. Initial experiments indicate that a RUBRIC rule set better matches human retrieval judgment than a standard Boolean keyword expression, given equal amounts of effort in defining each. The techniques presented may be useful in stand-alone retrieval systems, front-ends to existing information retrieval systems, or real-time document filtering and routing Index Terms-Artificial intelligence, evidential reasoning, expert systems, information retrieval.
Autonomous Agents & Multiagent Systems/International Conference on Autonomous Agents, 2004
In this paper we describe ICARUS, an integrated architecture for intelligent physical agents. The... more In this paper we describe ICARUS, an integrated architecture for intelligent physical agents. The framework supports long-term memories for hierarchical concepts and skills, along with mechanisms for recognizing concepts that hold in the environment, determining which skills are applicable, and selecting for execution the skill with the highest expected value. We illustrate these processes with examples from the domain of
isle.org
The paper abstract should begin in the left column, 0.* inches below the final address. The headi... more The paper abstract should begin in the left column, 0.* inches below the final address. The heading 'Abstract'should be centered, bold, and in** point type. The abstract body should use 10 point type, with a vertical spacing of** points, and should be indented ...
Cognitive Systems Research, 2009
In this paper, we present an approach to transfer that involves analogical mapping of symbols acr... more In this paper, we present an approach to transfer that involves analogical mapping of symbols across different domains. We relate this mechanism to ICARUS, a theory of the human cognitive architecture. Our system can transfer skills across domains hypothesizing maps between representations, improving performance in novel domains. Unlike previous approaches to analogical transfer, our method uses an explanatory analysis that compares how well a new domain theory explains previous solutions under different mapping hypotheses. We present experimental evidence that the new mechanism improves transfer over ICARUS' basic learning processes. Moreover, we argue that the same features which distinguish ICARUS from other architectures support representation mapping in a natural way and operate synergistically with it. These features enable our analogy system to translate a map among concepts into a map between skills, and to support transfer even if two domains are only partially analogous. We also discuss our system's relation to other work on analogy and outline directions for future research.
Developing autonomous agents for computer games is often a lengthy and expensive undertaking that... more Developing autonomous agents for computer games is often a lengthy and expensive undertaking that requires manual encoding of detailed and complex knowledge. In this paper we show how to acquire hierarchical skills for controlling a team of simulated football players by observing video of college football play. We then demonstrate the results in the Rush 2008 football simulator, showing that the learned skills have high fidelity with respect to the observed video and are robust to changes in the environment. Finally, we conclude with discussions of this work and of possible improvements.
2011 IEEE 24th International Conference on Micro Electro Mechanical Systems, 2011
s .................................................................................................. more s ....................................................................................................... 24 Author Index .................................................................................................. 40 Keyword Index ............................................................................................... 44
Computational Intelligence, 2007
IEEE Intelligent Systems, 2008
The European Commission's Information Society Technologies Advisory Group (Istag) introduced the ... more The European Commission's Information Society Technologies Advisory Group (Istag) introduced the concept of ambient intelligence. 1-3 Basically, AmI refers to a digital environment that proactively, but sensibly, supports people in their daily lives. 4 IEEE Intelligent Systems was one of the first publications to emphasize AmI's importance, with Nigel Shadbolt's editorial in the July/August 2003 issue. 5 Other concepts such as ubiquitous computing, pervasive computing, con text awareness, and embedded systems overlap with AmI, but there are distinctive differences. 6 The Istag reports define AmI at a concep tual level and identify important technologies for achieving it. In Ambient Intelligence: From Vision to Reality, Istag refers to these AmI components: smart materials, microelectromechanical systems and sensor technologies, embedded systems, ubiq uitous communications, I/O device technology, and adaptive software. 3 The report also mentions these intelligence components: media management and handling, natural interaction, computational intel ligence, context awareness, and emotional com puting. In our opinion, achieving AmI will require borrowing much more from artificial intelligence.