{"references": ["M.R. Akbarzadeh, H. Rezaei, and M.B. Naghibi. A fuzzy adaptive\nalgorithm for expertness based cooperative learning, application to\nherdin problem. In Proceedings of the 22nd International Conference\non the North American Fuzzy Information Processing Society, pages\n317-322, 2003.", "T. Arai, E. Pagello, and L.E. Parker. Advances in multi-robot systems.\nIn IEEE Transactions on Robotics and Automation, volume 18, pages\n655-661, 2002.", "C.M. Bishop. Neural networks for pattern recognition. Oxford\nUniversity Press, 1995.", "S. Edut and D. Eilam. Protean behaviour under barn-owl attack: voles\nalternate between freezing and fleeing and spiny mice flee in alternating\npatters. Behavioural Brain Research, 155:207-216, 2004.", "D. Floreano and S. Nolfi. Adaptive behavior in competing co-evolving\nspecies. In Proceedings of the fourth European Conference on Artificial\nLife, pages 378-387. MIT Press, 1997.", "J.P. Hespanha, M. Prandini, and S. Sastry. Probabilistic pursuit-evasion\ngames: A one-step nash approach. In Proceedings of the 39th IEEE\nConference on Decision and Control, pages 2432-2437, 2000.", "D.A. Humphries and P.M. Driver. Protean defence by prey animals.\nOecologia, 5:285-302, 1970.", "C. Laugier and R. Chatila, editors. Autonomous navigation in dynamic\nenvironments. Springer Berlin / Heidelberg, 2007.", "S.W. Lee. A bio-inspired group evasion behaviour. Technical report,\nDepartment of Computer Science, The University of North Carolina at\nChapel Hill, 2008.\n[10] G.F. Miller and D. Cliff. Co-evolution of pursuit and evasion I: biological\nand game-theoretic foundations. Technical Report CSRP311, School of\nCognitive and Computing Sciences, University of Sussex, 1994.\n[11] B. Scherrer and F. Charpillet. Cooperative co-learning: A modelbased\napproach for solving multi-agent reinforcement problems. In\nProceedings of the 14th International Conference on Tools with Artificial\nIntelligence, pages 463-468. IEEE Computer Society, 2002.\n[12] T. Stankowich and D.T. Blumstein. Fear in animals: a meta-analysis and\nreview of risk assessment. Proceedings B, 272(1581):2627-2634, 2005.\n[13] R.S. Sutton and A.G. Barto. Reinforcement Learning: An Introduction.\nThe MIT Press, 1998.\n[14] H. Tamakoshi and S. Ishii. Multi-agent reinforcement learning applied\nto a chase problem in a continuous world. Artificial Life Robotics,\n5:202-206, 2001.\n[15] N. Vlassis. A concise introduction to multi-agent systems and distributed\nartificial intelligence. Morgan & Claypool, 2007.\n[16] M. Wahde and M.G. Nordahl. Evolution of protean behavior in pursuitevasion\ncontests. In Proceedings of the fifth International Conference on\nSimulation of Adaptive Behavior on From animals to animats 5, pages\n557-561. MIT Press, 1998."]}

A novel biologically inspired controller for the autonomous navigation of a mobile robot in an evasion task is proposed. The controller takes advantage of the environment by calculating a measure of danger and subsequently choosing the parameters of a reinforcement learning based decision process. Two different reinforcement learning algorithms were used: Qlearning and Sarsa (λ). Simulations show that selecting dynamic parameters reduce the time while executing the decision making process, so the robot can obtain a policy to succeed in an escaping task in a realistic time.