Abstract
Sensor evolution in nature aims at improving the acquisition of information from the environment and is intimately related with selection pressure toward adaptivity and robustness. Our work in the area indicates that information theory can be applied to the perception-action loop. This letter studies the perception-action loop of agents, which is modeled as a causal Bayesian network. Finite state automata are evolved as agent controllers in a simple virtual world to maximize information flow through the perception-action loop. The information flow maximization organizes the agent's behavior as well as its information processing. To gain more insight into the results, the evolved implicit representations of space and time are analyzed in an information-theoretic manner, which paves the way toward a principled and general understanding of the mechanisms guiding the evolution of sensors in nature and provides insights into the design of mechanisms for artificial sensor evolution.
References
25
Referenced
45
10.1037/h0054663
10.1162/089976602760805368
{'issue': '2', 'key': 'p_6', 'first-page': '93', 'volume': '125', 'author': 'Ay N.', 'year': '2007', 'journal-title': 'Theory in Biosciences'}
/ Theory in Biosciences by Ay N. (2007)10.1016/S0893-6080(03)00190-4
10.1162/neco.1989.1.3.295
10.1080/net.12.3.241.253
10.1162/neco.1995.7.6.1129
10.1146/annurev.bb.16.060187.002323
10.1162/089976600300015259
10.1016/0305-0548(86)90048-1
10.1109/TSSC.1966.300074
10.1207/s15516709cog1903_1
10.1207/s15516709cog1804_1
10.1214/aoms/1177729694
10.1038/236
10.1109/2.36
{'key': 'p_34', 'first-page': '153', 'author': 'Nadal J.-P.', 'year': '1995', 'journal-title': 'International Journal of Neural Systems (Suppl.)'}
/ International Journal of Neural Systems (Suppl.) by Nadal J.-P. (1995)10.1162/neco.1992.4.6.863
10.1162/neco.1996.8.4.773
10.1523/JNEUROSCI.23-37-11539.2003
10.1002/j.1538-7305.1948.tb01338.x
10.1103/PhysRevLett.84.1156
10.1016/j.physa.2003.09.007
10.1111/1468-0017.00172
10.1162/0899766054615671
Dates
Type | When |
---|---|
Created | 18 years, 1 month ago (July 24, 2007, 1:08 p.m.) |
Deposited | 4 years, 5 months ago (March 12, 2021, 4:36 p.m.) |
Indexed | 1 month, 1 week ago (July 19, 2025, 11:48 p.m.) |
Issued | 18 years ago (Sept. 1, 2007) |
Published | 18 years ago (Sept. 1, 2007) |
Published Print | 18 years ago (Sept. 1, 2007) |
@article{Klyubin_2007, title={Representations of Space and Time in the Maximization of Information Flow in the Perception-Action Loop}, volume={19}, ISSN={1530-888X}, url={http://dx.doi.org/10.1162/neco.2007.19.9.2387}, DOI={10.1162/neco.2007.19.9.2387}, number={9}, journal={Neural Computation}, publisher={MIT Press - Journals}, author={Klyubin, Alexander S. and Polani, Daniel and Nehaniv, Chrystopher L.}, year={2007}, month=sep, pages={2387–2432} }