tingxun's picture
First training of SnowballTarget
db538ac verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.7844546437263489,
"min": 0.7844546437263489,
"max": 2.7944178581237793,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 39141.1484375,
"min": 39141.1484375,
"max": 141151.640625,
"count": 20
},
"SnowballTarget.Step.mean": {
"value": 999952.0,
"min": 49936.0,
"max": 999952.0,
"count": 20
},
"SnowballTarget.Step.sum": {
"value": 999952.0,
"min": 49936.0,
"max": 999952.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 14.047369956970215,
"min": 0.446770042181015,
"max": 14.047369956970215,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 14075.46484375,
"min": 443.1958923339844,
"max": 14075.46484375,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 50347.0,
"min": 48158.0,
"max": 50347.0,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 27.73913043478261,
"min": 5.037190082644628,
"max": 27.73913043478261,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 7018.0,
"min": 1219.0,
"max": 7018.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 27.73913043478261,
"min": 5.037190082644628,
"max": 27.73913043478261,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 7018.0,
"min": 1219.0,
"max": 7018.0,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.024471899460884745,
"min": 0.02110136260528634,
"max": 0.02561229946569074,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.12235949730442372,
"min": 0.08440545042114536,
"max": 0.1280614973284537,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.17242038685083388,
"min": 0.15438103044405577,
"max": 0.3238931970596314,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8621019342541695,
"min": 0.6175241217762231,
"max": 1.6194659852981568,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 8.380417206560002e-06,
"min": 8.380417206560002e-06,
"max": 0.0002920932026356,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 4.190208603280001e-05,
"min": 4.190208603280001e-05,
"max": 0.0013898592367135997,
"count": 20
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10279344000000001,
"min": 0.10279344000000001,
"max": 0.19736439999999997,
"count": 20
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.5139672000000001,
"min": 0.4299776,
"max": 0.9632863999999999,
"count": 20
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.00014939265600000004,
"min": 0.00014939265600000004,
"max": 0.00486848356,
"count": 20
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0007469632800000002,
"min": 0.0007469632800000002,
"max": 0.02316799136,
"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": "1746497860",
"python_version": "3.10.12 | packaged by conda-forge | (main, Jun 23 2023, 22:40:32) [GCC 12.3.0]",
"command_line_arguments": "/home/txshi/miniconda3/envs/hf-rl-ch5/bin/mlagents-learn ./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": "2.7.0+cu126",
"numpy_version": "1.23.5",
"end_time_seconds": "1746498569"
},
"total": 709.1388229509998,
"count": 1,
"self": 0.16646175100004257,
"children": {
"run_training.setup": {
"total": 0.009094104999803676,
"count": 1,
"self": 0.009094104999803676
},
"TrainerController.start_learning": {
"total": 708.963267095,
"count": 1,
"self": 0.6044152279819173,
"children": {
"TrainerController._reset_env": {
"total": 1.3000922839996747,
"count": 1,
"self": 1.3000922839996747
},
"TrainerController.advance": {
"total": 707.0031684790183,
"count": 90928,
"self": 0.5696742239565538,
"children": {
"env_step": {
"total": 506.8617856400333,
"count": 90928,
"self": 299.2319616621412,
"children": {
"SubprocessEnvManager._take_step": {
"total": 207.23350875200776,
"count": 90928,
"self": 2.252718222860949,
"children": {
"TorchPolicy.evaluate": {
"total": 204.98079052914682,
"count": 90928,
"self": 204.98079052914682
}
}
},
"workers": {
"total": 0.39631522588433654,
"count": 90928,
"self": 0.0,
"children": {
"worker_root": {
"total": 707.9836085219881,
"count": 90928,
"is_parallel": true,
"self": 446.9729496589207,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0006692749998364889,
"count": 1,
"is_parallel": true,
"self": 0.00018863699961002567,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0004806380002264632,
"count": 10,
"is_parallel": true,
"self": 0.0004806380002264632
}
}
},
"UnityEnvironment.step": {
"total": 0.009826122000049509,
"count": 1,
"is_parallel": true,
"self": 0.0001313720003963681,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0001350629995613417,
"count": 1,
"is_parallel": true,
"self": 0.0001350629995613417
},
"communicator.exchange": {
"total": 0.009181767999962176,
"count": 1,
"is_parallel": true,
"self": 0.009181767999962176
},
"steps_from_proto": {
"total": 0.0003779190001296229,
"count": 1,
"is_parallel": true,
"self": 8.528900116289151e-05,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00029262999896673136,
"count": 10,
"is_parallel": true,
"self": 0.00029262999896673136
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 261.0106588630674,
"count": 90927,
"is_parallel": true,
"self": 11.083211220931389,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.414907688028961,
"count": 90927,
"is_parallel": true,
"self": 5.414907688028961
},
"communicator.exchange": {
"total": 213.8126099880019,
"count": 90927,
"is_parallel": true,
"self": 213.8126099880019
},
"steps_from_proto": {
"total": 30.699929966105174,
"count": 90927,
"is_parallel": true,
"self": 6.000352090147317,
"children": {
"_process_rank_one_or_two_observation": {
"total": 24.699577875957857,
"count": 909270,
"is_parallel": true,
"self": 24.699577875957857
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 199.57170861502846,
"count": 90928,
"self": 0.7239496360166413,
"children": {
"process_trajectory": {
"total": 56.00508639601139,
"count": 90928,
"self": 53.50316079901086,
"children": {
"RLTrainer._checkpoint": {
"total": 2.501925597000536,
"count": 40,
"self": 2.501925597000536
}
}
},
"_update_policy": {
"total": 142.84267258300042,
"count": 95,
"self": 105.54861193698753,
"children": {
"TorchPPOOptimizer.update": {
"total": 37.294060646012895,
"count": 4750,
"self": 37.294060646012895
}
}
}
}
}
}
},
"trainer_threads": {
"total": 4.2700003177742474e-07,
"count": 1,
"self": 4.2700003177742474e-07
},
"TrainerController._save_models": {
"total": 0.05559067700005471,
"count": 1,
"self": 0.000957331999870803,
"children": {
"RLTrainer._checkpoint": {
"total": 0.05463334500018391,
"count": 1,
"self": 0.05463334500018391
}
}
}
}
}
}
}