Finding intrinsic rewards by embodied evolution and constrained reinforcement learning

Neural Networks

Volumn 21, Issue 10, 2008, Pages 1447-1455

  Uchibe, Eiji ^a   Doya, Kenji ^a,b,c  

^a OKINAWA INSTITUTE OF SCIENCE AND TECHNOLOGY GRADUATE UNIVERSITY   (Japan)

^b NARA INSTITUTE OF SCIENCE AND TECHNOLOGY   (Japan)

^c ADVANCED TELECOMMUNICATIONS RESEARCH INSTITUTE INTERNATIONAL   (Japan)

Author keywords

Cyber Rodents; Embodied evolution; Intrinsic and extrinsic rewards; Reinforcement learning

Indexed keywords

ARTIFICIAL INTELLIGENCE; AUTONOMOUS AGENTS; MAMMALS; ONLINE SYSTEMS; REINFORCEMENT; ROBOTICS; ROBOTS;

BATTERY PACKS; CYBER RODENT ROBOTS; CYBER RODENTS; DESIGN PRINCIPLES; EMBODIED EVOLUTION; EMBODIED EVOLUTIONS; HARDWARE EXPERIMENTS; INTERMEDIATE STATES; INTRINSIC AND EXTRINSIC REWARDS; INTRINSIC REWARDS; POLICY GRADIENT REINFORCEMENT LEARNINGS; REWARD FUNCTIONS;

REINFORCEMENT LEARNING;

ARTICLE; ARTIFICIAL INTELLIGENCE; COMPUTER PROGRAM; LEARNING; NEUROSCIENCE; PRIORITY JOURNAL; REINFORCEMENT; REWARD; ROBOTICS;

ALGORITHMS; ARTIFICIAL INTELLIGENCE; COMPUTERS; ELECTRIC POWER SUPPLIES; FEEDBACK; MODELS, THEORETICAL; REINFORCEMENT (PSYCHOLOGY); ROBOTICS; SOFTWARE; STOCHASTIC PROCESSES;

EID: 56949096913     PISSN: 08936080     EISSN: None     Source Type: Journal    
DOI: 10.1016/j.neunet.2008.09.013     Document Type: Article

References (22)

1. Barto, A.G., Singh, S., & Chentanez, N. (2004). Intrinsically motivated learning of hierarchical collections of skills. In Proc. of international conference on developmental learning
2. Baxter J., and Bartlett P.L. Infinite-horizon gradient-based policy search. Journal of Artificial Intelligence Research 15 (2001) 319-350
3. Doya K., and Uchibe E. The Cyber Rodent Project: Exploration of adaptive mechanisms for self-preservation and self-reproduction. Adaptive Behavior 13 (2005) 149-160
4. Elfwing, S. (2007). Embodied evolution of learning ability. Ph.D. thesis. Stockholm, Sweden: KTH School of Computer Science and Communication
5. Elfwing, S., Uchibe, E., Doya, K., & Christensen, H.I. Darwinian embodied evolution of the learning ability for survival. Adaptive Behavior (in press)
6. Eshelman L.J., and Schaffer J.D. Real-coded genetic algorithms and interval-schemata. Foundations of genetic algorithms 2 (1993), Morgan Kaufmann 187-202
7. Främling K. Guiding exploration by pre-existing knowledge without modifying reward. Neural Networks 20 6 (2007) 736-747
8. Kamioka T., Uchibe E., and Doya K. Max-min actor-critic for multiple reward reinforcement learning. IEICE TRANSACTIONS on Information and Systems J90-D (2007) 2510-2521 (in Japanese)
9. Konda V.R., and Tsitsiklis J.N. Actor-critic algorithms. SIAM Journal on Control and Optimization 42 4 (2003) 1143-1166
10. Meeden, L.A., Marshall, J.B., & Blank, D. (2004). Self-Motivated, Task-independent reinforcement learning for robots. In 2004 AAAI fall symposium on real-world reinforcement learning
11. Oudeyer, P.-Y., & Kaplan, F. (2004). Intelligent adaptive curiosity: A source of self-development. In Proc. of the 4th international workshop on epigenetic robotics(pp. 127-130)
12. Oudeyer P.-Y., Kaplan F., and Hafner V. Intrinsic motivation systems for autonomous mental development. IEEE Transactions on Evolutionary Computation 11 2 (2007) 265-286
13. Sato T., Uchibe E., and Doya K. Learning how, what, and whether to communicate: Emergence of protocommunication in reinforcement learning agents. Journal of Artificial Life and Robotics 12 (2008) 70-74
14. Singh S., Barto A.G., and Chentanez N. Intrinsically motivated reinforcement learning. In: Saul L.K., Weiss Y., Bottou, and L. (Eds). Advances in neural information processing systems 17 (2005), MIT Press 1281-1288
15. Stout, A., Konidaris, G.D., & Barto, A.G. (2005). Intrinsically motivated reinforcement learning: A promising framework for developmental robot learning. In Proc. of the AAAI spring symposium workshop on developmental robotics
16. Sutton R.S., and Barto A.G. Reinforcement learning (1998), MIT Press/Bradford Books
17. Uchibe E., and Doya K. Competitive-cooperative-concurrent reinforcement learning with importance sampling. In: Schaal S., Ijspeert A., Billard A., Vijayakumar S., Hallam J., and Meyer J.-A. (Eds). Proc. of the eighth international conference on simulation of adaptive behavior: From animals to animats 8 (2004), MIT Press, Cambridge, MA 287-296
18. Uchibe E., and Doya K. Constrained reinforcement learning from intrinsic and extrinsic rewards. Proc. of international conference on developmental learning (2007), IEEE, London, UK
19. Uchibe E., and Doya K. The Cyber Rodent Project: Learning and evolution under biological constraints. Proc. of the 14th international conference on neural information processing (2007), Springer, Berlin, Kitakushu, Japan
20. Usui, Y., & Arita, T. (2003). Situated and embodied evolution in collective evolutionary robotics. In Proc. of the 8th international symposium on artificial life and robotics (pp. 212-215)
21. Watson R.A., Ficici S.G., and Pollack J.B. Embodied evolution: Distributing an evolutionary algorithm in a population of robots. Robotics and Autonomous Systems 39 (2002) 1-18
22. Wischmann S., Stamm K., and Wörgötter F. Embodied evolution and learning: The neglected timing of maturation. Advances in artificial life: 9th European conference on artificial life (2007), Springer, Berlin, Lisbon, Portugal 284-293