Peter Stone and Manuela Veloso, `Beating a defender in robotic soccer: Memory-based learning of a continuous function', Technical Report CMU-CS-95-222, CMU CS, (1995).  Home/Search   Document Details and Download   Summary   Related Articles   Check

....trees that guide program synthesis. Soccer. To come up with a challenging scenario for our multiagent learning case study we decided on a non trivial soccer simulation. Soccer recently received much attention by various multiagent researchers (Sahota, 1993; Asada et al. 1994; Littman, 1994; Stone and Veloso, 1995; Matsubara et al. 1996) Most early research focused on physical coordination of soccer playing robots (Sahota, 1993; Asada et al. 1994) There also have been attempts to learn low level cooperation tasks such as pass play (Stone and Veloso, 1995; Matsubara et al. 1996) Recently Stone and ....

.... 1993; Asada et al. 1994; Littman, 1994; Stone and Veloso, 1995; Matsubara et al. 1996) Most early research focused on physical coordination of soccer playing robots (Sahota, 1993; Asada et al. 1994) There also have been attempts to learn low level cooperation tasks such as pass play (Stone and Veloso, 1995; Matsubara et al. 1996) Recently Stone and Veloso (1996) mentioned that even team strategies might be learnable by TD( or genetic methods. Published results on learning entire soccer strategies, however, have been limited to extremely reduced scenarios such as Littman s (1994) tiny 5 Theta 4 ....

Stone, P. and Veloso, M. (1995). Beating a defender in robotic soccer: Memory-based learning of a continuous function. In Tesauro, G., Touretzky, D. S., and Leen, T. K., editors, Advances in Neural Information Processing Systems 7. MIT Press, Cambridge MA.

.... 1996; Tan 1993) Problems in multi agent systems are distinct from problems in DAI and distributed computing, from which the field was derived, in that DAI and distributed computing focus on information processing and multi agent systems focus on behavior development and behavior management (Stone and Veloso 1995). In addition, problems in multi agent systems are distinct from problems in artificial life in that multi agent systems focus on individual behaviors and artificial life focuses on population dynamics (Collins 1992) So far, most work in learning and multi agent systems has emphasized multiple ....

Stone, P. and Veloso, M. (1995). Beating a defender in robotic soccer: Memory-based learning of a continuous function. In Proceedings of Neural Information Processing Systems.

....the question of learning to choose among actions in the presence of an adversary. This paper describes our work on applying memory based supervised learning techniques to acquire strategy knowledge that enables an agent to decide how to achieve a goal. For other work in the same domain, please see [12, 13]. The input to the learning task includes a continuous valued range of the position of the adversary. This raises the question of how to discretize the space of values into a set of learned features. We present our empirical studies and results on learning an appropriate generalization degree in ....

Peter Stone and Manucla Veloso. Beating a defender in robotic soccer: Memory-based learning of a continuous function. In David S. Tourctzky, Michael C. Mozcr, and Michael E. Hassclmo, editors, Advances in Neural Information Processing Systems 8, Cambridge, MA, 1996. MIT press.

....planning. Along with the real robot competition, RoboCup97 will also include a simulator based tournament using the Soccer Server system designed by Noda [ Noda, 1995 ] While we continue working on our real world system, we have been concurrently developing learning techniques in simulation [ Stone and Veloso, 1997; 1996 ] We eventually hope to transfer these learning techniques to the real system as we develop a complete Robotic Soccer architecture. This paper describes the overall architecture of our robotic soccer system. The combination of robust hardware, real time vision, and intelligent control code ....

....that can perform visual captures at frame rate. By engineering the input scene in an appropriate manner, we found that a fast general purpose processor (a 166MHz Pentium processor) is adequate for the task. 4. 1 Detection and Association Following the techniques used by many teams in MIROSOT [ Stone et al. 1996 ] we have decided to use color as a cue for the vision system to detect. This colorbased system allows the use of fixed color space thresholds to segment the different colors into regions. Each robot is fitted with two colors to differentiate the team and the orientation. We considered using ....

[Article contains additional citation context not shown here]

Peter Stone and Manuela Veloso. Beating a defender in robotic soccer: Memorybased learning of a continuous function. In David S. Touretzky, Michael C. Mozer, and Michael E. Hasselmo, editors, Advances in Neural Information Processing Systems 8, pages 896--902, Cambridge, MA, 1996. MIT press.

....the ball, to arbitrarily complex reasoning procedures that take into account the actions and perceived strategies of teammates and opponents. Opportunities, and indeed demands, for innovative and novel techniques abound. Robotic Soccer systems have been recently developed both in simulation [6, 9, 12, 14] and with real robots [1, 4, 10, 11, 15, 13] While robotic systems are difficult, expensive, and time consuming to use, they provide a certain degree of realism that is never possible in simulation. On the other hand, simulators allow researchers to isolate key issues, implement complex ....

Peter Stone and Manuela Veloso. Beating a defender in robotic soccer: Memorybased learning of a continuous function. In David S. Touretzky, Michael C. Mozer, and Michael E. Hasselmo, editors, Advances in Neural Information Processing Systems 8, pages 896--902, Cambridge, MA, 1996. MIT press.

....Table 2, turn up in robotic soccer. As well as addressing most of the issues inherent in MAS, robotic soccer is a great domain for multiagent Machine Learning. In another soccer simulator, Stone and Veloso use Memory based Learning to allow a player to learn when to shoot and when to pass the ball [78]. They then use Neural Networks to teach a player to shoot a moving ball into the goal [79] They use similar techniques in the soccerserver system as well, extending the learned behavior as a part of a hierarchical learning system [80] Matsubar et al. also use a Neural Network to allow a player ....

P. Stone and M. Veloso, "Beating a defender in robotic soccer: Memory-based learning of a continuous function," in Advances in Neural Information Processing Systems 8 (D. S. Touretzky, M. C. Mozer, and M. E. Hasselmo, eds.), (Cambridge, MA), pp. 896--902, MIT press, 1996.

....playing Robotic Soccer. We are not the first to build robots for this domain [ Asada et al. 1994a; Sahota et al. 1995 ] however our system is distinctly different from the others about which we know. Furthermore, with at least two Robotic Soccer competitions planned during the next two years [ Stone et al. 1996; Kitano et al. 1997 ] there will surely be several more systems built in the near future. The purpose of this paper is to describe our current mini robot system in as much detail as possible, so that others may benefit from both our setbacks and our successes. We aim for this paper to render ....

....well as ours and probably many others will come together at least twice in the next two years. In November 1996, there will be a Micro Robot competition in Taejon, Korea called MIROSOT96. The call for participation is a good example of one possible set of precise specifications for this domain [ Stone et al. 1996 ] Planning is also in progress for the 1997 robot soccer competition at IJCAI, to be called RoboCup97 [ Kitano et al. 1997 ] Along with the real robot competition, RoboCup97 will also include a simulator based tournament using the Soccer Server system designed by Noda [ Noda, 1995 ] While ....

[Article contains additional citation context not shown here]

Peter Stone and Manuela Veloso. Beating a defender in robotic soccer: Memorybased learning of a continuous function. In David S. Touretzky, Michael C. Mozer, and Michael E. Hasselmo, editors, Advances in Neural Information Processing Systems 8, pages 896--902, Cambridge, MA, 1996. MIT press.

.... Decision Tree Confidence Factors for Multiagent Control Peter Stone and Manuela Veloso Computer Science Department Carnegie Mellon University Pittsburgh, PA 15213 fpstone,velosog cs.cmu.edu http: www.cs.cmu.edu f pstone, mmvg Keywords: multiagent systems, machine learning, decision trees Abstract Although Decision Trees are widely used for classification tasks, they are ....

Peter Stone and Manuela Veloso. Beating a defender in robotic soccer: Memory-based learning of a continuous function. In David S. Touretzky, Michael C. Mozer, and Michael E. Hasselmo, editors, Advances in Neural Information Processing Systems 8, pages 896--902, Cambridge, MA, 1996. MIT press.

....8.3 Robotic Soccer Many other robotic soccer systems have been developed both in simulation and with real robots. Using a simulator based closely upon the Dynasim system [28] we previously used Memory based Learning to allow a player to learn when to shoot and when to pass the ball [31]. We then used Neural Networks to teach a player to shoot a moving ball into the goal [35] In the soccer server, we then layered two learned behaviors to produce a higher level multi agent behavior: passing [34] Also in the soccer server Matsubara et al. used a Neural Network to allow a player ....

Peter Stone and Manuela Veloso. Beating a defender in robotic soccer: Memory-based learning of a continuous function. In David S. Touretzky, Michael C. Mozer, and Michael E. Hasselmo, editors, Advances in Neural Information Processing Systems 8, pages 896--902, Cambridge, MA, 1996. MIT Press.

.... and memorybased learning [ Aha and Salzberg, 1994, Kanazawa, 1994, Kuh et al. 1991, Moore, 1991, Salganicoff, 1993, Schlimmer and Granger, 1986, Sutton and Whitehead, 1993, Wettschereck and Dietterich, 1994, Winstead and Christiansen, 1994 ] particularly as it relates to this paper, please see [ Stone and Veloso, 1995a ] The input to our learning task includes a continuous valued range of the position of the adversary. This raises the question of how to discretize the space of values into a set of learned features. Due to the cost of learning and reusing a large set of specialized instances, we notice a clear ....

....the adversary. This raises the question of how to discretize the space of values into a set of learned features. Due to the cost of learning and reusing a large set of specialized instances, we notice a clear advantage to having an appropriate degree of generalization. For more details please see [ Stone and Veloso, 1995a ] Here, we address the issue of the effect of differences between past episodes and the current situation. We performed extensive experiments, training the system under particular conditions and then testing it (with learning continuing incrementally) in nondeterministic variations of the ....

[Article contains additional citation context not shown here]

Peter Stone and Manuela Veloso. Beating a defender in robotic soccer: Memory-based learning of a continuous function. Technical Report CMU-CS-95-222, Computer Science Department, Carnegie Mellon University, 1995.

....the question of learning to choose among actions in the presence of an adversary. This paper describes our work on applying memory based supervised learning techniques to acquire strategy knowledge that enables an agent to decide how to achieve a goal. For other work in the same domain, please see [12, 13]. The input to the learning task includes a continuous valued range of the position of the adversary. This raises the question of how to discretize the space of values into a set of learned features. We present our empirical studies and results on learning an appropriate generalization degree in ....

Peter Stone and Manuela Veloso. Beating a defender in robotic soccer: Memory-based learning of a continuous function. In David S. Touretzky, Michael C. Mozer, and Michael E. Hasselmo, editors, Advances in Neural Information Processing Systems 8, Cambridge, MA, 1996. MIT press.

No context found.

Stone, P., & Veloso, M. (1996a). Beating a defender in robotic soccer: Memory-based learning of a continuous function. In Touretzky, D. S., Mozer, M. C., & Hasselmo, M. E. (Eds.), Advances in Neural Information Processing Systems 8 Cambridge, MA. MIT press.

....Machine Learning in Robotic Soccer As well as addressing most of the issues inherent in MAS, robotic soccer is a great domain for multiagent Machine Learning. In another soccer simulator, Stone and Veloso use Memory based Learning to allow a player to learn when to shoot and when to pass the ball [82]. They then use Neural Networks to teach a player to shoot a moving ball into the goal [83] They use similar techniques in the soccerserver system as well, extending the learned behavior as a part of a hierarchical learning system [84] Matsubara et al. also use a Neural Network to allow a player ....

Peter Stone and Manuela Veloso. Beating a defender in robotic soccer: Memory-based learning of a continuous function. In David S. Touretzky, Michael C. Mozer, and Michael E. Hasselmo, editors, Advances in Neural Information Processing Systems 8, pages 896--902, Cambridge, MA, 1996. MIT press.

.... Ford et al. used a Reinforcement Learning (RL) approach with sensory predicates to learn to choose among low level behaviors [5] Using a simulator based closely upon the Dynasim system, Stone and Veloso used Memory based Learning to allow a player to learn when to shoot and when to pass the ball [19]. They then used Neural Networks to teach a player to shoot a moving ball into the goal [21] In the RoboCup Soccer Server Matsubar et al. used a Neural Network to allow a player to learn when to shoot and when to pass [11] as opposed to the Memory based technique used by Stone and Veloso for a ....

Peter Stone and Manuela Veloso. Beating a defender in robotic soccer: Memory-based learning of a continuous function. In David S. Touretzky, Michael C. Mozer, and Michael E. Hasselmo, editors, Advances in Neural Information Processing Systems 8, pages 896--902, Cambridge, MA, 1996. MIT press.

No context found.

Peter Stone and Manuela Veloso, `Beating a defender in robotic soccer: Memory-based learning of a continuous function', Technical Report CMU-CS-95-222, CMU CS, (1995).

No context found.

Page 30 Stone, P., and Veloso, M. 1996a. Beating a defender in robotic soccer: Memory-based learning of a continuous function. Advances in Neural Information Processing Systems, ed., Touretzky, D. S., Mozer, M. C., and Hasselmo, M. E.

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC