SpriteLi's picture
First Push
794d7b0 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9767401814460754,
"min": 0.9767401814460754,
"max": 2.867901086807251,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9282.9384765625,
"min": 9282.9384765625,
"max": 29275.53515625,
"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": 12.141406059265137,
"min": 0.4924221932888031,
"max": 12.141406059265137,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2367.57421875,
"min": 95.5299072265625,
"max": 2431.400390625,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06399493021707908,
"min": 0.06169670019481405,
"max": 0.07819783561680392,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.25597972086831633,
"min": 0.25597972086831633,
"max": 0.3909891780840196,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.21326456628009385,
"min": 0.12611590999443378,
"max": 0.2952577146829344,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8530582651203754,
"min": 0.5044636399777351,
"max": 1.4762885734146718,
"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": 24.204545454545453,
"min": 3.4545454545454546,
"max": 24.204545454545453,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1065.0,
"min": 152.0,
"max": 1328.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.204545454545453,
"min": 3.4545454545454546,
"max": 24.204545454545453,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1065.0,
"min": 152.0,
"max": 1328.0,
"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": "1756032687",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./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": "1756033109"
},
"total": 421.619155436,
"count": 1,
"self": 0.4384027750002133,
"children": {
"run_training.setup": {
"total": 0.024274605999949017,
"count": 1,
"self": 0.024274605999949017
},
"TrainerController.start_learning": {
"total": 421.15647805499987,
"count": 1,
"self": 0.34911912799952916,
"children": {
"TrainerController._reset_env": {
"total": 2.7935766069999772,
"count": 1,
"self": 2.7935766069999772
},
"TrainerController.advance": {
"total": 417.9329875950003,
"count": 18192,
"self": 0.36405646198886643,
"children": {
"env_step": {
"total": 299.97701371701066,
"count": 18192,
"self": 231.4073024920201,
"children": {
"SubprocessEnvManager._take_step": {
"total": 68.35398263899265,
"count": 18192,
"self": 1.2615456389810333,
"children": {
"TorchPolicy.evaluate": {
"total": 67.09243700001161,
"count": 18192,
"self": 67.09243700001161
}
}
},
"workers": {
"total": 0.21572858599790834,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 419.85246938198406,
"count": 18192,
"is_parallel": true,
"self": 216.35694921499328,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.004768315999967854,
"count": 1,
"is_parallel": true,
"self": 0.0033436989999700018,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001424616999997852,
"count": 10,
"is_parallel": true,
"self": 0.001424616999997852
}
}
},
"UnityEnvironment.step": {
"total": 0.03633614399996077,
"count": 1,
"is_parallel": true,
"self": 0.0006713909999689349,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003918329999805792,
"count": 1,
"is_parallel": true,
"self": 0.0003918329999805792
},
"communicator.exchange": {
"total": 0.03316921500004355,
"count": 1,
"is_parallel": true,
"self": 0.03316921500004355
},
"steps_from_proto": {
"total": 0.0021037049999677038,
"count": 1,
"is_parallel": true,
"self": 0.0003907049999725132,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017129999999951906,
"count": 10,
"is_parallel": true,
"self": 0.0017129999999951906
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 203.4955201669908,
"count": 18191,
"is_parallel": true,
"self": 9.796914034011138,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.375958745991625,
"count": 18191,
"is_parallel": true,
"self": 5.375958745991625
},
"communicator.exchange": {
"total": 156.24588214399057,
"count": 18191,
"is_parallel": true,
"self": 156.24588214399057
},
"steps_from_proto": {
"total": 32.07676524299745,
"count": 18191,
"is_parallel": true,
"self": 5.747427794971259,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.329337448026195,
"count": 181910,
"is_parallel": true,
"self": 26.329337448026195
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 117.5919174160008,
"count": 18192,
"self": 0.4225210420112262,
"children": {
"process_trajectory": {
"total": 26.705398223989505,
"count": 18192,
"self": 26.264593702989373,
"children": {
"RLTrainer._checkpoint": {
"total": 0.4408045210001319,
"count": 4,
"self": 0.4408045210001319
}
}
},
"_update_policy": {
"total": 90.46399815000007,
"count": 90,
"self": 37.34001042300656,
"children": {
"TorchPPOOptimizer.update": {
"total": 53.123987726993505,
"count": 4587,
"self": 53.123987726993505
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0010001005866798e-06,
"count": 1,
"self": 1.0010001005866798e-06
},
"TrainerController._save_models": {
"total": 0.0807937239999319,
"count": 1,
"self": 0.00088784499985195,
"children": {
"RLTrainer._checkpoint": {
"total": 0.07990587900007995,
"count": 1,
"self": 0.07990587900007995
}
}
}
}
}
}
}