20240219_reinforcement learning_pong PPO training log 1200e.md

20240218_pong-PPO.ipynb
👉 training log for reference
1000 episodes, T4 GPU, Wall time: 1h 38min 14s

Episode: 20, score: -15.750000
[-16. -16. -16. -16. -16. -16. -16. -14.]
Episode: 40, score: -12.625000
[-13. -13. -12. -11. -12. -12. -16. -12.]
Episode: 60, score: -13.500000
[-14. -12. -17. -15. -16.  -8. -12. -14.]
Episode: 80, score: -13.750000
[-15. -15. -14. -13. -15. -13. -11. -14.]
Episode: 100, score: -13.625000
[-15. -11. -15. -13. -16. -12. -13. -14.]
Episode: 120, score: -13.750000
[-16. -12. -13. -14. -15. -11. -13. -16.]
Episode: 140, score: -12.625000
[-16. -11. -11. -11. -14. -12. -14. -12.]
Episode: 160, score: -11.625000
[-12. -12. -11. -14. -11.  -9. -12. -12.]
Episode: 180, score: -7.000000
[-5. -7. -7. -9. -5. -5. -9. -9.]
Episode: 200, score: -3.500000
[-5. -4. -6. -5. -1.  0.  0. -7.]
Episode: 220, score: -1.125000
[-4.  0. -2. -3.  0.  0.  0.  0.]
Episode: 240, score: -2.125000
[ 0. -3.  0. -1. -2. -1. -5. -5.]
Episode: 260, score: -1.125000
[-1.  0.  0. -4.  1. -1.  1. -5.]
Episode: 280, score: 1.750000
[-1.  3.  1.  4.  2.  2.  0.  3.]
Episode: 300, score: 3.125000
[4. 3. 3. 3. 3. 1. 4. 4.]
Episode: 320, score: 3.500000
[5. 2. 5. 4. 0. 5. 2. 5.]
Episode: 340, score: 2.875000
[ 0.  5.  5. -3.  3.  5.  5.  3.]
Episode: 360, score: 3.375000
[ 5.  5.  5. -1. -2.  5.  5.  5.]
Episode: 380, score: 4.625000
[5. 5. 5. 5. 5. 5. 2. 5.]
Episode: 400, score: 5.000000
[5. 5. 5. 5. 5. 5. 5. 5.]
Episode: 420, score: 5.000000
[5. 5. 5. 5. 5. 5. 5. 5.]
Episode: 440, score: 1.750000
[-2.  5. -2.  5.  0. -2.  5.  5.]
Episode: 460, score: 3.875000
[ 5.  3.  5.  5. -2.  5.  5.  5.]
Episode: 480, score: 4.875000
[5. 5. 5. 5. 5. 5. 5. 4.]
Episode: 500, score: 5.000000
[5. 5. 5. 5. 5. 5. 5. 5.]
Episode: 520, score: 5.000000
[5. 5. 5. 5. 5. 5. 5. 5.]
Episode: 540, score: 4.125000
[-2.  5.  5.  5.  5.  5.  5.  5.]
Episode: 560, score: 4.875000
[5. 5. 4. 5. 5. 5. 5. 5.]
Episode: 580, score: 4.750000
[5. 5. 5. 5. 5. 5. 3. 5.]
Episode: 600, score: 5.000000
[5. 5. 5. 5. 5. 5. 5. 5.]
Episode: 620, score: 4.125000
[ 5.  5.  5. -2.  5.  5.  5.  5.]
Episode: 640, score: 5.000000
[5. 5. 5. 5. 5. 5. 5. 5.]
Episode: 660, score: 3.750000
[ 5.  3.  5. -3.  5.  5.  5.  5.]
Episode: 680, score: 5.000000
[5. 5. 5. 5. 5. 5. 5. 5.]
Episode: 700, score: 4.125000
[ 5.  5.  5.  5.  5.  5.  5. -2.]
Episode: 720, score: 5.000000
[5. 5. 5. 5. 5. 5. 5. 5.]
Episode: 740, score: 5.000000
[5. 5. 5. 5. 5. 5. 5. 5.]
Episode: 760, score: 5.000000
[5. 5. 5. 5. 5. 5. 5. 5.]
Episode: 780, score: 5.000000
[5. 5. 5. 5. 5. 5. 5. 5.]
Episode: 800, score: 4.750000
[5. 5. 5. 5. 5. 5. 3. 5.]
Episode: 820, score: 4.750000
[5. 5. 5. 5. 5. 5. 3. 5.]
Episode: 840, score: 5.000000
[5. 5. 5. 5. 5. 5. 5. 5.]
Episode: 860, score: 3.125000
[ 5. -3.  5.  5.  5.  5.  5. -2.]
Episode: 880, score: 5.000000
[5. 5. 5. 5. 5. 5. 5. 5.]
Episode: 900, score: 5.000000
[5. 5. 5. 5. 5. 5. 5. 5.]
Episode: 920, score: 4.250000
[ 5.  5.  5.  5. -1.  5.  5.  5.]
Episode: 940, score: 5.000000
[5. 5. 5. 5. 5. 5. 5. 5.]
Episode: 960, score: 4.375000
[5. 5. 0. 5. 5. 5. 5. 5.]
Episode: 980, score: 5.000000
[5. 5. 5. 5. 5. 5. 5. 5.]
Episode: 1000, score: 5.000000
[5. 5. 5. 5. 5. 5. 5. 5.]
Episode: 1020, score: 5.000000
[5. 5. 5. 5. 5. 5. 5. 5.]
Episode: 1040, score: 5.000000
[5. 5. 5. 5. 5. 5. 5. 5.]
Episode: 1060, score: 5.000000
[5. 5. 5. 5. 5. 5. 5. 5.]
Episode: 1080, score: 5.000000
[5. 5. 5. 5. 5. 5. 5. 5.]
Episode: 1100, score: 5.000000
[5. 5. 5. 5. 5. 5. 5. 5.]
Episode: 1120, score: 5.000000
[5. 5. 5. 5. 5. 5. 5. 5.]
Episode: 1140, score: 5.000000
[5. 5. 5. 5. 5. 5. 5. 5.]
Episode: 1160, score: 5.000000
[5. 5. 5. 5. 5. 5. 5. 5.]
Episode: 1180, score: 5.000000
[5. 5. 5. 5. 5. 5. 5. 5.]
Episode: 1200, score: 5.000000
[5. 5. 5. 5. 5. 5. 5. 5.]