lin267's picture
value-based 实践:Q-Learning 智能体(FrozenLake + Taxi) + 回放视频 + 评估分数
c3d6fc9 verified
Raw History Blame Contribute Delete
12.4 kB
{
"run": "taxi",
"env_id": "Taxi-v3",
"env_kwargs": {},
"n_training_episodes": 25000,
"n_episodes": 100,
"mean_reward": 7.56,
"std_reward": 2.706732347314747,
"min_reward": 3.0,
"max_reward": 15.0,
"success_rate": 1.0,
"mean_steps": 13.44,
"policy": "greedy (argmax Q)",
"model_file": "models\\qtable_taxi.pkl",
"qtable_shape": [
500,
6
],
"qtable_nonzero": 2398,
"evaluated_at": "2026-10-30T22:47:35",
"episodes": [
{
"episode": 1,
"seed": 16,
"reward": 6.0,
"steps": 15,
"success": 1
},
{
"episode": 2,
"seed": 54,
"reward": 12.0,
"steps": 9,
"success": 1
},
{
"episode": 3,
"seed": 165,
"reward": 12.0,
"steps": 9,
"success": 1
},
{
"episode": 4,
"seed": 177,
"reward": 11.0,
"steps": 10,
"success": 1
},
{
"episode": 5,
"seed": 191,
"reward": 7.0,
"steps": 14,
"success": 1
},
{
"episode": 6,
"seed": 191,
"reward": 7.0,
"steps": 14,
"success": 1
},
{
"episode": 7,
"seed": 120,
"reward": 4.0,
"steps": 17,
"success": 1
},
{
"episode": 8,
"seed": 80,
"reward": 7.0,
"steps": 14,
"success": 1
},
{
"episode": 9,
"seed": 149,
"reward": 5.0,
"steps": 16,
"success": 1
},
{
"episode": 10,
"seed": 178,
"reward": 4.0,
"steps": 17,
"success": 1
},
{
"episode": 11,
"seed": 48,
"reward": 5.0,
"steps": 16,
"success": 1
},
{
"episode": 12,
"seed": 38,
"reward": 11.0,
"steps": 10,
"success": 1
},
{
"episode": 13,
"seed": 6,
"reward": 11.0,
"steps": 10,
"success": 1
},
{
"episode": 14,
"seed": 125,
"reward": 4.0,
"steps": 17,
"success": 1
},
{
"episode": 15,
"seed": 174,
"reward": 4.0,
"steps": 17,
"success": 1
},
{
"episode": 16,
"seed": 73,
"reward": 7.0,
"steps": 14,
"success": 1
},
{
"episode": 17,
"seed": 50,
"reward": 5.0,
"steps": 16,
"success": 1
},
{
"episode": 18,
"seed": 172,
"reward": 11.0,
"steps": 10,
"success": 1
},
{
"episode": 19,
"seed": 100,
"reward": 7.0,
"steps": 14,
"success": 1
},
{
"episode": 20,
"seed": 148,
"reward": 6.0,
"steps": 15,
"success": 1
},
{
"episode": 21,
"seed": 146,
"reward": 7.0,
"steps": 14,
"success": 1
},
{
"episode": 22,
"seed": 6,
"reward": 11.0,
"steps": 10,
"success": 1
},
{
"episode": 23,
"seed": 25,
"reward": 3.0,
"steps": 18,
"success": 1
},
{
"episode": 24,
"seed": 40,
"reward": 6.0,
"steps": 15,
"success": 1
},
{
"episode": 25,
"seed": 68,
"reward": 11.0,
"steps": 10,
"success": 1
},
{
"episode": 26,
"seed": 148,
"reward": 6.0,
"steps": 15,
"success": 1
},
{
"episode": 27,
"seed": 49,
"reward": 4.0,
"steps": 17,
"success": 1
},
{
"episode": 28,
"seed": 167,
"reward": 9.0,
"steps": 12,
"success": 1
},
{
"episode": 29,
"seed": 9,
"reward": 6.0,
"steps": 15,
"success": 1
},
{
"episode": 30,
"seed": 97,
"reward": 9.0,
"steps": 12,
"success": 1
},
{
"episode": 31,
"seed": 164,
"reward": 6.0,
"steps": 15,
"success": 1
},
{
"episode": 32,
"seed": 176,
"reward": 6.0,
"steps": 15,
"success": 1
},
{
"episode": 33,
"seed": 61,
"reward": 10.0,
"steps": 11,
"success": 1
},
{
"episode": 34,
"seed": 7,
"reward": 10.0,
"steps": 11,
"success": 1
},
{
"episode": 35,
"seed": 54,
"reward": 12.0,
"steps": 9,
"success": 1
},
{
"episode": 36,
"seed": 55,
"reward": 5.0,
"steps": 16,
"success": 1
},
{
"episode": 37,
"seed": 161,
"reward": 9.0,
"steps": 12,
"success": 1
},
{
"episode": 38,
"seed": 131,
"reward": 11.0,
"steps": 10,
"success": 1
},
{
"episode": 39,
"seed": 184,
"reward": 6.0,
"steps": 15,
"success": 1
},
{
"episode": 40,
"seed": 51,
"reward": 8.0,
"steps": 13,
"success": 1
},
{
"episode": 41,
"seed": 170,
"reward": 5.0,
"steps": 16,
"success": 1
},
{
"episode": 42,
"seed": 12,
"reward": 5.0,
"steps": 16,
"success": 1
},
{
"episode": 43,
"seed": 120,
"reward": 4.0,
"steps": 17,
"success": 1
},
{
"episode": 44,
"seed": 113,
"reward": 6.0,
"steps": 15,
"success": 1
},
{
"episode": 45,
"seed": 95,
"reward": 10.0,
"steps": 11,
"success": 1
},
{
"episode": 46,
"seed": 126,
"reward": 15.0,
"steps": 6,
"success": 1
},
{
"episode": 47,
"seed": 51,
"reward": 8.0,
"steps": 13,
"success": 1
},
{
"episode": 48,
"seed": 98,
"reward": 4.0,
"steps": 17,
"success": 1
},
{
"episode": 49,
"seed": 36,
"reward": 7.0,
"steps": 14,
"success": 1
},
{
"episode": 50,
"seed": 135,
"reward": 7.0,
"steps": 14,
"success": 1
},
{
"episode": 51,
"seed": 54,
"reward": 12.0,
"steps": 9,
"success": 1
},
{
"episode": 52,
"seed": 82,
"reward": 11.0,
"steps": 10,
"success": 1
},
{
"episode": 53,
"seed": 45,
"reward": 9.0,
"steps": 12,
"success": 1
},
{
"episode": 54,
"seed": 95,
"reward": 10.0,
"steps": 11,
"success": 1
},
{
"episode": 55,
"seed": 89,
"reward": 9.0,
"steps": 12,
"success": 1
},
{
"episode": 56,
"seed": 59,
"reward": 6.0,
"steps": 15,
"success": 1
},
{
"episode": 57,
"seed": 95,
"reward": 10.0,
"steps": 11,
"success": 1
},
{
"episode": 58,
"seed": 124,
"reward": 4.0,
"steps": 17,
"success": 1
},
{
"episode": 59,
"seed": 9,
"reward": 6.0,
"steps": 15,
"success": 1
},
{
"episode": 60,
"seed": 113,
"reward": 6.0,
"steps": 15,
"success": 1
},
{
"episode": 61,
"seed": 58,
"reward": 7.0,
"steps": 14,
"success": 1
},
{
"episode": 62,
"seed": 85,
"reward": 14.0,
"steps": 7,
"success": 1
},
{
"episode": 63,
"seed": 51,
"reward": 8.0,
"steps": 13,
"success": 1
},
{
"episode": 64,
"seed": 134,
"reward": 4.0,
"steps": 17,
"success": 1
},
{
"episode": 65,
"seed": 121,
"reward": 6.0,
"steps": 15,
"success": 1
},
{
"episode": 66,
"seed": 169,
"reward": 10.0,
"steps": 11,
"success": 1
},
{
"episode": 67,
"seed": 105,
"reward": 6.0,
"steps": 15,
"success": 1
},
{
"episode": 68,
"seed": 21,
"reward": 8.0,
"steps": 13,
"success": 1
},
{
"episode": 69,
"seed": 30,
"reward": 8.0,
"steps": 13,
"success": 1
},
{
"episode": 70,
"seed": 11,
"reward": 5.0,
"steps": 16,
"success": 1
},
{
"episode": 71,
"seed": 50,
"reward": 5.0,
"steps": 16,
"success": 1
},
{
"episode": 72,
"seed": 65,
"reward": 11.0,
"steps": 10,
"success": 1
},
{
"episode": 73,
"seed": 12,
"reward": 5.0,
"steps": 16,
"success": 1
},
{
"episode": 74,
"seed": 43,
"reward": 5.0,
"steps": 16,
"success": 1
},
{
"episode": 75,
"seed": 82,
"reward": 11.0,
"steps": 10,
"success": 1
},
{
"episode": 76,
"seed": 145,
"reward": 8.0,
"steps": 13,
"success": 1
},
{
"episode": 77,
"seed": 152,
"reward": 7.0,
"steps": 14,
"success": 1
},
{
"episode": 78,
"seed": 97,
"reward": 9.0,
"steps": 12,
"success": 1
},
{
"episode": 79,
"seed": 106,
"reward": 7.0,
"steps": 14,
"success": 1
},
{
"episode": 80,
"seed": 55,
"reward": 5.0,
"steps": 16,
"success": 1
},
{
"episode": 81,
"seed": 31,
"reward": 9.0,
"steps": 12,
"success": 1
},
{
"episode": 82,
"seed": 85,
"reward": 14.0,
"steps": 7,
"success": 1
},
{
"episode": 83,
"seed": 38,
"reward": 11.0,
"steps": 10,
"success": 1
},
{
"episode": 84,
"seed": 112,
"reward": 9.0,
"steps": 12,
"success": 1
},
{
"episode": 85,
"seed": 102,
"reward": 8.0,
"steps": 13,
"success": 1
},
{
"episode": 86,
"seed": 168,
"reward": 7.0,
"steps": 14,
"success": 1
},
{
"episode": 87,
"seed": 123,
"reward": 6.0,
"steps": 15,
"success": 1
},
{
"episode": 88,
"seed": 97,
"reward": 9.0,
"steps": 12,
"success": 1
},
{
"episode": 89,
"seed": 21,
"reward": 8.0,
"steps": 13,
"success": 1
},
{
"episode": 90,
"seed": 83,
"reward": 10.0,
"steps": 11,
"success": 1
},
{
"episode": 91,
"seed": 158,
"reward": 4.0,
"steps": 17,
"success": 1
},
{
"episode": 92,
"seed": 26,
"reward": 7.0,
"steps": 14,
"success": 1
},
{
"episode": 93,
"seed": 80,
"reward": 7.0,
"steps": 14,
"success": 1
},
{
"episode": 94,
"seed": 63,
"reward": 5.0,
"steps": 16,
"success": 1
},
{
"episode": 95,
"seed": 5,
"reward": 11.0,
"steps": 10,
"success": 1
},
{
"episode": 96,
"seed": 81,
"reward": 9.0,
"steps": 12,
"success": 1
},
{
"episode": 97,
"seed": 32,
"reward": 3.0,
"steps": 18,
"success": 1
},
{
"episode": 98,
"seed": 11,
"reward": 5.0,
"steps": 16,
"success": 1
},
{
"episode": 99,
"seed": 28,
"reward": 4.0,
"steps": 17,
"success": 1
},
{
"episode": 100,
"seed": 148,
"reward": 6.0,
"steps": 15,
"success": 1
}
],
"evaluation_seconds": 0.02
}