Individual learning of coordination knowledge

Abstract. Social agents, both human and computational, inhabiting a world containing multiple active agents, need to coordinate their activities. This is because agents share resources, and without proper coordination or ‘rules of the road’, everybody will be interfering with the plans of others. As such, we need coordination schemes that allow agents to effectively achieve local goals without adversely affecting the problem-solving capabilities of other agents. Researchers in the field of Distributed Artificial Intelligence (DAI) have developed a variety of coordination schemes under different assumptions about agent capabilities and relationships. Whereas some of these researchers have been motivated by human cognitive biases, others have approached it as an engineering problem of designing the most effective coordination architecture or protocol. We evaluate individual and concurrent learning by multiple, autonomous agents as a means for acquiring coordination knowledge. We show that a uniform reinforcement learning algorithm suffices as a coordination mechanism in both cooperative and adversarial situations. Using a number of multi-agent learning scenarios with both tight and loose coupling between agents and with immediate as well as delayed feedback, we demonstrate that agents can consistently develop effective policies to coordinate their actions without explicit information sharing. We demonstrate the viabilityof using both the Q-learning algorithm and genetic algorithm based classifier systems with different pay-off schemes, namely the bucket brigade algorithm (BBA) and the profit sharing plan (PSP), for developing agent coordination on two different multi-agent domains. In addition, we show that a semi-random scheme for action selection is preferable to the more traditional fitness proportionate selection scheme used in classifier systems.     

Heuristic solution to the scheduling problems in flexible manufacturing system

The scheduling problems in flexible manufacturing systems deal with (1) tool allocation (2)parts scheduling (3) pallets scheduling (4) machines scheduling and (5) material handling equipment scheduling. This paper presents an approach to determine an optimal schedule of parts integrating all the above scheduling criteria. The problem is formulated as a hierarchical process and solved through eigenvector analysis of priority ordering. Effectiveness of the heuristic is illustrated with an example.     

Effect of individual opinions on group interactions

We have evaluated the effectiveness of a probabilistic reciprocity scheme for promoting co-operation among self-interested agents. The probabilistic reciprocity mechanism is used to determine whether an agent should co-operate when approached for help by another agent. The situation becomes more complex when a group of agents seeks help from another group. The opinions of the members of the helping group about each of the asking group members can be combined to evaluate such a request for help. Exploitative agents would want to be part of groups that receive help from other groups, but will try to prevent its group from helping other groups. Such agents, revealing false opinion about the reputation of others, can cause unwarranted rejection of help requests from other groups. This leads to global performance degradation in terms of reduced inter-group co-operation and increased cost for the individual agents. We study the viability of reciprocative agents in randomly formed groups and when groups are formed by agents contracting other helpful agents. Group helping decisions are based on both average and worst combined ratings of group members. A key result from our study is that lying exploitative agents, who provide false opinions about other agents, become ineffective when focused group selection is enabled.     

Correlation between optical emission spectra and the process parameters of a 915 MHz microwave plasma CVD reactor used for depositing polycrystalline diamond coatings

In this paper, the hydrogen and hydrogen-methane mixed plasma have been generated inside a 33 cm diameter quartz bell jar with a low power (9 KW) and lower frequency 915 MHz microwave plasma chemical vapor deposition system. The reactor is being used for growing polycrystalline diamond (PCD) over large area (100 mm). The generated plasma is diagnosed by in situ optical emission spectroscopy method with wave length ranging from 200 to 900 nm. The effects of microwave power, chamber pressure and gas concentration on plasma characteristics have been studied in this work. Within the optical range, Balmer H _α , H _β , C₂swan band and CH lines have been detected at the wavelengths of 655.95, 485.7, 515.82 and 430.17 nm, respectively. It has been observed that for hydrogen plasma, the amount of transition from hydrogen atom inner shell 3 to 2 (H _α ) is almost constant with increasing microwave (MW) power (from 2000 to 2800 W) and pressure (from 15 to 30 Torr) initially, after that it increases with further increase of MW power and pressure, whereas, the transition from 4 to 2 (H _β ) is slowly increased with increasing MW power and pressure. For hydrogen-methane plasma, intensities of C₂ swan band, i.e., the transitions from D³π _g to A³π _μ energy levels, are also increased with the increasing microwave power and reactor pressure. It has been observed that the radicals present in the plasma are affected by variation of different reactor parameters like pressure, MW power, CH₄ concentration, etc.