Sunazow's picture
First Push
e46cf39 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9564743041992188,
"min": 0.9441210031509399,
"max": 2.821655511856079,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9090.33203125,
"min": 9090.33203125,
"max": 28803.458984375,
"count": 20
},
"SnowballTarget.Step.mean": {
"value": 199984.0,
"min": 9952.0,
"max": 199984.0,
"count": 20
},
"SnowballTarget.Step.sum": {
"value": 199984.0,
"min": 9952.0,
"max": 199984.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 13.151178359985352,
"min": 0.42765122652053833,
"max": 13.214547157287598,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2564.479736328125,
"min": 82.96434020996094,
"max": 2695.767578125,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.07463564036166359,
"min": 0.061437807355404786,
"max": 0.07463564036166359,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.29854256144665436,
"min": 0.24916377362587455,
"max": 0.3579961505581071,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20682010799646378,
"min": 0.13539261949207523,
"max": 0.2781604150784951,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8272804319858551,
"min": 0.5415704779683009,
"max": 1.3717493409035253,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 8.082097306000005e-06,
"min": 8.082097306000005e-06,
"max": 0.000291882002706,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 3.232838922400002e-05,
"min": 3.232838922400002e-05,
"max": 0.00138516003828,
"count": 20
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10269400000000001,
"min": 0.10269400000000001,
"max": 0.19729400000000002,
"count": 20
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.41077600000000003,
"min": 0.41077600000000003,
"max": 0.96172,
"count": 20
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.0001444306000000001,
"min": 0.0001444306000000001,
"max": 0.0048649706,
"count": 20
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0005777224000000004,
"min": 0.0005777224000000004,
"max": 0.023089828,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 8756.0,
"min": 8756.0,
"max": 10945.0,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 25.25,
"min": 3.909090909090909,
"max": 26.072727272727274,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1111.0,
"min": 172.0,
"max": 1434.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.25,
"min": 3.909090909090909,
"max": 26.072727272727274,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1111.0,
"min": 172.0,
"max": 1434.0,
"count": 20
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1778668061",
"python_version": "3.10.12 (main, Mar 3 2026, 11:56:32) [GCC 11.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn /content/ml-agents/config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.8.0+cu128",
"numpy_version": "1.23.5",
"end_time_seconds": "1778668518"
},
"total": 456.5922361070001,
"count": 1,
"self": 0.4828329020001547,
"children": {
"run_training.setup": {
"total": 0.022728724999979022,
"count": 1,
"self": 0.022728724999979022
},
"TrainerController.start_learning": {
"total": 456.08667447999994,
"count": 1,
"self": 0.36427942100215205,
"children": {
"TrainerController._reset_env": {
"total": 3.0616738740000073,
"count": 1,
"self": 3.0616738740000073
},
"TrainerController.advance": {
"total": 452.585568034998,
"count": 18192,
"self": 0.38371081898128523,
"children": {
"env_step": {
"total": 329.96885387500515,
"count": 18192,
"self": 258.0690709709892,
"children": {
"SubprocessEnvManager._take_step": {
"total": 71.67931272799444,
"count": 18192,
"self": 1.2859476280042372,
"children": {
"TorchPolicy.evaluate": {
"total": 70.3933650999902,
"count": 18192,
"self": 70.3933650999902
}
}
},
"workers": {
"total": 0.22047017602153574,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 454.2148032540257,
"count": 18192,
"is_parallel": true,
"self": 227.17055911803254,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.004331008000008296,
"count": 1,
"is_parallel": true,
"self": 0.0029786210002384905,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013523869997698057,
"count": 10,
"is_parallel": true,
"self": 0.0013523869997698057
}
}
},
"UnityEnvironment.step": {
"total": 0.036081718000104956,
"count": 1,
"is_parallel": true,
"self": 0.0006162590000258206,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00047524299998258357,
"count": 1,
"is_parallel": true,
"self": 0.00047524299998258357
},
"communicator.exchange": {
"total": 0.03299244100003307,
"count": 1,
"is_parallel": true,
"self": 0.03299244100003307
},
"steps_from_proto": {
"total": 0.001997775000063484,
"count": 1,
"is_parallel": true,
"self": 0.0003998490000185484,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015979260000449358,
"count": 10,
"is_parallel": true,
"self": 0.0015979260000449358
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 227.04424413599315,
"count": 18191,
"is_parallel": true,
"self": 10.476223823978671,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.6412184370076375,
"count": 18191,
"is_parallel": true,
"self": 5.6412184370076375
},
"communicator.exchange": {
"total": 172.14508335901212,
"count": 18191,
"is_parallel": true,
"self": 172.14508335901212
},
"steps_from_proto": {
"total": 38.781718515994726,
"count": 18191,
"is_parallel": true,
"self": 6.853941161966532,
"children": {
"_process_rank_one_or_two_observation": {
"total": 31.927777354028194,
"count": 181910,
"is_parallel": true,
"self": 31.927777354028194
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 122.23300334101157,
"count": 18192,
"self": 0.43462358601914275,
"children": {
"process_trajectory": {
"total": 27.458439359991416,
"count": 18192,
"self": 27.02062601099135,
"children": {
"RLTrainer._checkpoint": {
"total": 0.4378133490000664,
"count": 4,
"self": 0.4378133490000664
}
}
},
"_update_policy": {
"total": 94.33994039500101,
"count": 90,
"self": 38.24231712499545,
"children": {
"TorchPPOOptimizer.update": {
"total": 56.097623270005556,
"count": 4587,
"self": 56.097623270005556
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.055999973686994e-06,
"count": 1,
"self": 1.055999973686994e-06
},
"TrainerController._save_models": {
"total": 0.07515209399980449,
"count": 1,
"self": 0.000683621999769457,
"children": {
"RLTrainer._checkpoint": {
"total": 0.07446847200003504,
"count": 1,
"self": 0.07446847200003504
}
}
}
}
}
}
}