q-learning.txt

Q Table after 100 episodes:

{('232', 3): 16.20037376, ('402', 2): -10, ('542', 1): -1, ('112', 3): -3.9982243225600005, ('432', 3): -1.72, ('502', 0): -10, ('142', 2): -2.2384000000000004, ('522', 1): -1.8639999999999999, ('422', 3): -2.7556480000000003, ('212', 0): -2.6464384, ('122', 3): -3.1968787456000003, ('152', 3): -2.2384000000000004, ('002', 0): 8.411342686026806, ('132', 2): 44.12233362176282, ('042', 1): -2.61856, ('022', 0): 44.6555181064926, ('412', 0): -2.9975680000000002, ('522', 2): -2.2384000000000004, ('332', 3): 61.283741696000014, ('222', 0): -2.4112, ('242', 3): -1.72, ('002', 3): -10.0, ('032', 2): 33.51311907200001, ('332', 1): -1.72, ('302', 3): -3.3681396736000004, ('512', 3): -2.4860800000000003, ('202', 3): -3.168045568, ('432', 2): -2.2384000000000004, ('312', 2): -3.0374271999999998, ('352', 2): -1, ('252', 3): -2.2384000000000004, ('222', 3): 38.25551450617728, ('012', 0): -3.831929344, ('052', 3): -10, ('532', 1): -1.0, ('322', 1): -2.4112, ('102', 2): -10.0, ('342', 1): 89.0, ('252', 0): 88.856, ('232', 0): 40.39619010560001, ('542', 2): -1, ('112', 2): -3.51442819072, ('502', 1): -2.9918080000000002, ('142', 3): -2.3824, ('432', 1): 71.0, ('422', 2): -1.8639999999999999, ('212', 1): 54.648764123639594, ('122', 0): -2.666944, ('152', 2): -2.3824, ('342', 2): 27.792470528000013, ('132', 1): -2.51488, ('042', 0): -2.5148800000000002, ('022', 3): -10.0, ('432', 0): -1.72, ('412', 1): -2.3824, ('142', 0): -1.8927999999999998, ('522', 3): -2.3824, ('422', 1): -1.8639999999999999, ('402', 0): -2.9918080000000002, ('152', 1): -10, ('242', 2): 49.392800000000015, ('002', 2): -10.0, ('032', 3): -10.0, ('042', 3): -10, ('302', 0): -3.1092659200000003, ('512', 2): -2.9918080000000002, ('202', 2): -10.0, ('412', 2): -3.4057630720000005, ('312', 1): -2.62432, ('352', 1): -10, ('112', 1): -3.3505131520000004, ('402', 3): -3.4065925120000005, ('222', 2): -2.9918080000000002, ('242', 1): 49.9472, ('032', 0): 54.95390000000001, ('012', 1): 42.61265900000001, ('512', 1): -2.5148800000000002, ('052', 0): -2.51488, ('532', 0): -10, ('202', 1): 38.02739241697281, ('322', 2): -2.4860800000000003, ('102', 3): -4.292149427108578, ('252', 1): -10, ('232', 1): 70.19000000000001, ('442', 1): 100.0, ('012', 2): 25.256979823497126, ('542', 3): -1, ('532', 3): -1.72, ('502', 2): -10, ('212', 2): -2.61856, ('102', 0): 17.584988529396295, ('122', 1): 54.90554792524621, ('342', 3): -1, ('332', 2): -2.2384000000000004, ('132', 0): 62.171000000000014, ('232', 2): 54.453081073951594, ('022', 2): -3.188947456, ('542', 0): -10, ('112', 0): 37.08941064427016, ('142', 1): -2.3824, ('522', 0): -10, ('422', 0): -1.8639999999999999, ('122', 2): -3.7108993024, ('152', 0): 62.38880000000001, ('002', 1): 37.35139310000001, ('132', 3): 46.390674921070115, ('042', 2): -3.1537792000000002, ('302', 1): -3.2193510400000003, ('022', 1): 48.45851000000001, ('412', 3): -2.983744, ('312', 0): -2.7844480000000003, ('352', 0): 100.0, ('332', 0): -1.72, ('222', 1): 62.16990704655607, ('242', 0): 79.10000000000001, ('402', 1): -3.1090355200000004, ('032', 1): -3.1092659200000003, ('302', 2): -10, ('512', 0): -10.0, ('052', 1): -10, ('202', 0): -3.6370127872, ('552', 3): 100, ('322', 3): -2.6104960000000004, ('312', 3): -3.1867264000000004, ('352', 3): 60.488000000000014, ('252', 2): -1.72, ('442', 0): -1, ('012', 3): -10.0, ('052', 2): -2.8302976000000006, ('532', 2): -1.72, ('502', 3): -3.012544, ('322', 0): -2.3824, ('212', 3): -3.8043476992, ('102', 1): -3.8554430464000005, ('342', 0): 88.28}