000			00558nam a2200157Ia 4500
008			240527b |||||||| |||| 00| 0 eng d
082			_a006.31 N96
100			_aRavindran, B.
245			_aSolution of delayed reinforcement learning problems having continuous action spaces _cby B Ravindran
260			_aBangalore : _bIndian Institute of Science, _c1996.
300			_aiii, 75 p. : _bill.
500			_aInclude bibliographical references
502			_aMSc(Engg);1996;Computer Science of Automation
700			_aAdvised by Keerthi, S.Sathiya
942			_cT
999			_c66308 _d66308