Vitao2's picture
First Push
fea489b verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.375552773475647,
"min": 1.375552773475647,
"max": 2.890312671661377,
"count": 50
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 13194.302734375,
"min": 13194.302734375,
"max": 29719.04296875,
"count": 50
},
"SnowballTarget.Step.mean": {
"value": 499976.0,
"min": 9952.0,
"max": 499976.0,
"count": 50
},
"SnowballTarget.Step.sum": {
"value": 499976.0,
"min": 9952.0,
"max": 499976.0,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 10.885025024414062,
"min": -0.10575587302446365,
"max": 10.885025024414062,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2231.43017578125,
"min": -20.516639709472656,
"max": 2231.43017578125,
"count": 50
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 50
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 8756.0,
"max": 10945.0,
"count": 50
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 22.763636363636362,
"min": 2.7454545454545456,
"max": 23.136363636363637,
"count": 50
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1252.0,
"min": 134.0,
"max": 1252.0,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 22.763636363636362,
"min": 2.7454545454545456,
"max": 23.136363636363637,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1252.0,
"min": 134.0,
"max": 1252.0,
"count": 50
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 50
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 50
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.0242631427347078,
"min": 0.014358070676098577,
"max": 0.03100192411802709,
"count": 47
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.0242631427347078,
"min": 0.014358070676098577,
"max": 0.03100192411802709,
"count": 47
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.3205221086740494,
"min": 0.10399579753478368,
"max": 0.3272521376609802,
"count": 47
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.3205221086740494,
"min": 0.10399579753478368,
"max": 0.3272521376609802,
"count": 47
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 5.2176982607999905e-06,
"min": 5.2176982607999905e-06,
"max": 0.00029345280218239997,
"count": 47
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 5.2176982607999905e-06,
"min": 5.2176982607999905e-06,
"max": 0.00029345280218239997,
"count": 47
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10173919999999997,
"min": 0.10173919999999997,
"max": 0.19781759999999993,
"count": 47
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.10173919999999997,
"min": 0.10173919999999997,
"max": 0.19781759999999993,
"count": 47
},
"SnowballTarget.Policy.Beta.mean": {
"value": 9.678607999999983e-05,
"min": 9.678607999999983e-05,
"max": 0.004891098240000001,
"count": 47
},
"SnowballTarget.Policy.Beta.sum": {
"value": 9.678607999999983e-05,
"min": 9.678607999999983e-05,
"max": 0.004891098240000001,
"count": 47
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1773169870",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn /content/config/ppo/SnowballTarget.yaml --env=/content/ml-agents/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": "1773170872"
},
"total": 1002.5718057369997,
"count": 1,
"self": 0.4331886099996609,
"children": {
"run_training.setup": {
"total": 0.025886271999979726,
"count": 1,
"self": 0.025886271999979726
},
"TrainerController.start_learning": {
"total": 1002.1127308550001,
"count": 1,
"self": 0.8923561159510882,
"children": {
"TrainerController._reset_env": {
"total": 3.2889335400000164,
"count": 1,
"self": 3.2889335400000164
},
"TrainerController.advance": {
"total": 997.8597960190491,
"count": 45464,
"self": 0.9204856740930154,
"children": {
"env_step": {
"total": 807.0358883409858,
"count": 45464,
"self": 631.1067086959297,
"children": {
"SubprocessEnvManager._take_step": {
"total": 175.37342395402175,
"count": 45464,
"self": 3.2190043750279074,
"children": {
"TorchPolicy.evaluate": {
"total": 172.15441957899384,
"count": 45464,
"self": 172.15441957899384
}
}
},
"workers": {
"total": 0.5557556910343919,
"count": 45464,
"self": 0.0,
"children": {
"worker_root": {
"total": 997.8607868530125,
"count": 45464,
"is_parallel": true,
"self": 443.16205123203736,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0029046970000763395,
"count": 1,
"is_parallel": true,
"self": 0.001540357999601838,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013643390004745015,
"count": 10,
"is_parallel": true,
"self": 0.0013643390004745015
}
}
},
"UnityEnvironment.step": {
"total": 0.03757043199993859,
"count": 1,
"is_parallel": true,
"self": 0.0008037079996938701,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00040885900011744525,
"count": 1,
"is_parallel": true,
"self": 0.00040885900011744525
},
"communicator.exchange": {
"total": 0.03431275499997355,
"count": 1,
"is_parallel": true,
"self": 0.03431275499997355
},
"steps_from_proto": {
"total": 0.002045110000153727,
"count": 1,
"is_parallel": true,
"self": 0.0003820269998868753,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016630830002668517,
"count": 10,
"is_parallel": true,
"self": 0.0016630830002668517
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 554.6987356209752,
"count": 45463,
"is_parallel": true,
"self": 25.81330273602225,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 13.828162998007201,
"count": 45463,
"is_parallel": true,
"self": 13.828162998007201
},
"communicator.exchange": {
"total": 421.2958141549393,
"count": 45463,
"is_parallel": true,
"self": 421.2958141549393
},
"steps_from_proto": {
"total": 93.76145573200643,
"count": 45463,
"is_parallel": true,
"self": 16.67872272119166,
"children": {
"_process_rank_one_or_two_observation": {
"total": 77.08273301081476,
"count": 454630,
"is_parallel": true,
"self": 77.08273301081476
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 189.90342200397026,
"count": 45464,
"self": 1.0375267019926468,
"children": {
"process_trajectory": {
"total": 65.45130230597715,
"count": 45464,
"self": 65.31962320397679,
"children": {
"RLTrainer._checkpoint": {
"total": 0.13167910200036204,
"count": 1,
"self": 0.13167910200036204
}
}
},
"_update_policy": {
"total": 123.41459299600047,
"count": 47,
"self": 95.79286521399558,
"children": {
"TorchPPOOptimizer.update": {
"total": 27.621727782004882,
"count": 1410,
"self": 27.621727782004882
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.48999968386488e-07,
"count": 1,
"self": 9.48999968386488e-07
},
"TrainerController._save_models": {
"total": 0.07164423099993655,
"count": 1,
"self": 0.0005585450003309234,
"children": {
"RLTrainer._checkpoint": {
"total": 0.07108568599960563,
"count": 1,
"self": 0.07108568599960563
}
}
}
}
}
}
}