value-based-qlearning / metrics.json
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
1.25 kB
{
"frozenlake4x4": {
"env_id": "FrozenLake-v1",
"n_episodes": 100,
"mean_reward": 1.0,
"std_reward": 0.0,
"success_rate": 1.0,
"mean_steps": 6.0,
"qtable_shape": [
16,
4
],
"qtable_nonzero": 35,
"evaluated_at": "2026-10-30T22:46:48"
},
"frozenlake4x4_slippery": {
"env_id": "FrozenLake-v1",
"n_episodes": 100,
"mean_reward": 0.74,
"std_reward": 0.4386342439892262,
"success_rate": 0.74,
"mean_steps": 39.41,
"qtable_shape": [
16,
4
],
"qtable_nonzero": 44,
"evaluated_at": "2026-10-30T22:46:59"
},
"frozenlake8x8": {
"env_id": "FrozenLake-v1",
"n_episodes": 100,
"mean_reward": 1.0,
"std_reward": 0.0,
"success_rate": 1.0,
"mean_steps": 14.0,
"qtable_shape": [
64,
4
],
"qtable_nonzero": 179,
"evaluated_at": "2026-10-30T22:47:24"
},
"taxi": {
"env_id": "Taxi-v3",
"n_episodes": 100,
"mean_reward": 7.56,
"std_reward": 2.706732347314747,
"success_rate": 1.0,
"mean_steps": 13.44,
"qtable_shape": [
500,
6
],
"qtable_nonzero": 2398,
"evaluated_at": "2026-10-30T22:47:35"
}
}