A major challenge in multi-agent reinforcement learning remains dealing with the large state spac... more A major challenge in multi-agent reinforcement learning remains dealing with the large state spaces typ- ically associated with realistic multi-agent systems. As the state space grows, agent policies become more and more complex and learning slows down. Current more advanced single-agent techniques are already very capable of learning optimal policies in large unknown environments. When multiple agents are present however,
In this paper we propose a model to feature selection based on ant colony and rough set theory (R... more In this paper we propose a model to feature selection based on ant colony and rough set theory (RST). The objective is to find the reducts. RST offers the heuristic function to measure the quality of one feature subset. We have studied three variants of ant's algorithms and the influence of the parameters on the performance both in terms of
ABSTRACT When controlling a complex system consisting of several subsystems, a simple divide and ... more ABSTRACT When controlling a complex system consisting of several subsystems, a simple divide and conquer approach is to design a controller for each system separately. However, this does not necessarily result in a good overall control behavior. Especially when there are strong interactions between the subsystems, the selfish behavior of one controller might deteriorate the performance of the other subsystems. An alternative approach is to design a global controller for the entire mechatronic system. Such a design procedure might result in more optimal behavior, however it requires a lot more effort, especially when the interactions between the different subsystems cannot be modeled exactly or if the number of parameters is large. In this paper we present a hybrid approach to this problem that overcomes the problems encountered when using several independent subsystems. Starting from such a system with individual subsystem controllers, we add a global layer which uses reinforcement learning to simultaneously tune the lower level controllers. While each subsystem still has its own individual controller, the reinforcement learning layer is used to tune these controllers in order to optimize global system behavior. This mitigates both the problem of subsystems behaving selfishly without the added complexity of designing a global controller for the entire system. Our approach is validated on a hydrostatic drive train.
We propose an extended ACO algorithm for the Maximum Edge Disjoint Paths (MEDP) problem. In this ... more We propose an extended ACO algorithm for the Maximum Edge Disjoint Paths (MEDP) problem. In this problem we want to satisfy the largest possible number of request for disjoint paths on a given graph topology. We first proposed our approach in [1]. In that paper a proof of concept was given on a number of quite small graphs. Now we
ANTS - Ant Colony Optimization and Swarm Intelligence, 2004
In this paper we propose the Multi-type Ant Colony system, which is an extension of the well know... more In this paper we propose the Multi-type Ant Colony system, which is an extension of the well known Ant System. Unlike the Ant System the ants are of a predefined type. In the Multi-type Ant Colony System ants have the same goal as their fellow types ants, however are in competition with the ants of different types. The collaborative behavior
ABSTRACT In this paper we introduce a reinforcement learning approach to optimize the wire profil... more ABSTRACT In this paper we introduce a reinforcement learning approach to optimize the wire profile generated by an automated wire winding machine. The wire winder spools wire onto large bobbins, while trying to maintain an even wire profile across the bobbin. Uneven profiles that contain bumps or gaps (i.e. areas with too much or too little wire) lead to snagged or breaking wires when the bobbin is unwound. By setting the turning points of the traversal system which distributes the wire over a spinning bobbin, a controller can influence the amount of wire spooled on the edges of the bobbin. The behavior of the wire, however, is highly non-deterministic and difficult to model with sufficient accuracy, making the application of a model based controller technique very difficult. This fact makes reinforcement learning a promising approach to apply here, as this technique can learn optimal policies relying only on interactions with the plant. We apply a learning algorithm called continuous reinforcement learning automata and empirically demonstrate that this technique can successfully optimize the wire profile, even on rounded bobbins that require continuous adaptation of the turning point.
A major challenge in multi-agent reinforcement learning remains dealing with the large state spac... more A major challenge in multi-agent reinforcement learning remains dealing with the large state spaces typ- ically associated with realistic multi-agent systems. As the state space grows, agent policies become more and more complex and learning slows down. Current more advanced single-agent techniques are already very capable of learning optimal policies in large unknown environments. When multiple agents are present however,
In this paper we propose a model to feature selection based on ant colony and rough set theory (R... more In this paper we propose a model to feature selection based on ant colony and rough set theory (RST). The objective is to find the reducts. RST offers the heuristic function to measure the quality of one feature subset. We have studied three variants of ant's algorithms and the influence of the parameters on the performance both in terms of
ABSTRACT When controlling a complex system consisting of several subsystems, a simple divide and ... more ABSTRACT When controlling a complex system consisting of several subsystems, a simple divide and conquer approach is to design a controller for each system separately. However, this does not necessarily result in a good overall control behavior. Especially when there are strong interactions between the subsystems, the selfish behavior of one controller might deteriorate the performance of the other subsystems. An alternative approach is to design a global controller for the entire mechatronic system. Such a design procedure might result in more optimal behavior, however it requires a lot more effort, especially when the interactions between the different subsystems cannot be modeled exactly or if the number of parameters is large. In this paper we present a hybrid approach to this problem that overcomes the problems encountered when using several independent subsystems. Starting from such a system with individual subsystem controllers, we add a global layer which uses reinforcement learning to simultaneously tune the lower level controllers. While each subsystem still has its own individual controller, the reinforcement learning layer is used to tune these controllers in order to optimize global system behavior. This mitigates both the problem of subsystems behaving selfishly without the added complexity of designing a global controller for the entire system. Our approach is validated on a hydrostatic drive train.
We propose an extended ACO algorithm for the Maximum Edge Disjoint Paths (MEDP) problem. In this ... more We propose an extended ACO algorithm for the Maximum Edge Disjoint Paths (MEDP) problem. In this problem we want to satisfy the largest possible number of request for disjoint paths on a given graph topology. We first proposed our approach in [1]. In that paper a proof of concept was given on a number of quite small graphs. Now we
ANTS - Ant Colony Optimization and Swarm Intelligence, 2004
In this paper we propose the Multi-type Ant Colony system, which is an extension of the well know... more In this paper we propose the Multi-type Ant Colony system, which is an extension of the well known Ant System. Unlike the Ant System the ants are of a predefined type. In the Multi-type Ant Colony System ants have the same goal as their fellow types ants, however are in competition with the ants of different types. The collaborative behavior
ABSTRACT In this paper we introduce a reinforcement learning approach to optimize the wire profil... more ABSTRACT In this paper we introduce a reinforcement learning approach to optimize the wire profile generated by an automated wire winding machine. The wire winder spools wire onto large bobbins, while trying to maintain an even wire profile across the bobbin. Uneven profiles that contain bumps or gaps (i.e. areas with too much or too little wire) lead to snagged or breaking wires when the bobbin is unwound. By setting the turning points of the traversal system which distributes the wire over a spinning bobbin, a controller can influence the amount of wire spooled on the edges of the bobbin. The behavior of the wire, however, is highly non-deterministic and difficult to model with sufficient accuracy, making the application of a model based controller technique very difficult. This fact makes reinforcement learning a promising approach to apply here, as this technique can learn optimal policies relying only on interactions with the plant. We apply a learning algorithm called continuous reinforcement learning automata and empirically demonstrate that this technique can successfully optimize the wire profile, even on rounded bobbins that require continuous adaptation of the turning point.
Uploads
Papers by Peter Vrancx