Total params: 721
Trainable params: 721
Non-trainable params: 0
_________________________________________________________________
episode: 0 score: -1351.4228103970006 mean: -1351.42 std: 0.0 max: -1351.4228103970006
episode: 1 score: -1229.4448082548686 mean: -1290.43 std: 60.99 max: -1229.4448082548686
episode: 2 score: -1779.3128634691002 mean: -1453.39 std: 235.78 max: -1229.4448082548686
episode: 3 score: -1493.4884369596273 mean: -1463.42 std: 204.93 max: -1229.4448082548686
episode: 4 score: -1808.6403583082629 mean: -1532.46 std: 229.49 max: -1229.4448082548686
episode: 5 score: -1305.9792964969897 mean: -1494.71 std: 225.86 max: -1229.4448082548686
episode: 6 score: -1565.1599365676377 mean: -1504.78 std: 210.55 max: -1229.4448082548686
episode: 7 score: -1195.8300375690574 mean: -1466.16 std: 221.88 max: -1195.8300375690574
episode: 8 score: -1580.4307272874496 mean: -1478.86 std: 212.25 max: -1195.8300375690574
episode: 9 score: -1511.0179680557023 mean: -1482.07 std: 201.59 max: -1195.8300375690574
episode: 10 score: -1549.2786325126337 mean: -1501.86 std: 197.46 max: -1195.8300375690574
episode: 11 score: -929.2999418137911 mean: -1471.84 std: 251.9 max: -929.2999418137911
episode: 12 score: -1381.753542917903 mean: -1432.09 std: 230.71 max: -929.2999418137911
episode: 13 score: -1597.700823282343 mean: -1442.51 std: 235.55 max: -929.2999418137911
episode: 14 score: -1644.6114526600206 mean: -1426.11 std: 214.23 max: -929.2999418137911
episode: 15 score: -1575.421705624693 mean: -1453.05 std: 214.38 max: -929.2999418137911
episode: 16 score: -1175.1149058942365 mean: -1414.05 std: 225.62 max: -929.2999418137911
episode: 17 score: -1850.361085326904 mean: -1479.5 std: 246.77 max: -929.2999418137911
episode: 18 score: nan mean: nan std: nan max: -929.2999418137911
episode: 19 score: nan mean: nan std: nan max: -929.2999418137911
episode: 20 score: nan mean: nan std: nan max: -929.2999418137911
episode: 21 score: nan mean: nan std: nan max: -929.2999418137911
episode: 22 score: nan mean: nan std: nan max: -929.2999418137911
episode: 23 score: nan mean: nan std: nan max: -929.2999418137911
episode: 24 score: nan mean: nan std: nan max: -929.2999418137911
episode: 25 score: nan mean: nan std: nan max: -929.2999418137911
#just continues like this...