CharithAnupama's picture
Unit 5 – SnowballTarget trained agent
f0b5f84 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.5942128300666809,
"min": 0.5907962322235107,
"max": 2.8461508750915527,
"count": 60
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 6065.724609375,
"min": 5614.92724609375,
"max": 29053.5078125,
"count": 60
},
"SnowballTarget.Step.mean": {
"value": 599936.0,
"min": 9952.0,
"max": 599936.0,
"count": 60
},
"SnowballTarget.Step.sum": {
"value": 599936.0,
"min": 9952.0,
"max": 599936.0,
"count": 60
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 13.95268440246582,
"min": 0.43592292070388794,
"max": 13.969010353088379,
"count": 60
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2706.82080078125,
"min": 84.56904602050781,
"max": 2853.96435546875,
"count": 60
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06672232127754137,
"min": 0.06093354117525879,
"max": 0.0785931639274007,
"count": 60
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.26688928511016546,
"min": 0.24373416470103515,
"max": 0.376565044903306,
"count": 60
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19103649839320605,
"min": 0.1350636001900021,
"max": 0.29415416010454587,
"count": 60
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7641459935728242,
"min": 0.5402544007600084,
"max": 1.4707708005227293,
"count": 60
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 2.4940991686666686e-06,
"min": 2.4940991686666686e-06,
"max": 0.00029729400090199997,
"count": 60
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 9.976396674666675e-06,
"min": 9.976396674666675e-06,
"max": 0.00146172001276,
"count": 60
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10083133333333334,
"min": 0.10083133333333334,
"max": 0.19909800000000002,
"count": 60
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.40332533333333337,
"min": 0.40332533333333337,
"max": 0.9872400000000001,
"count": 60
},
"SnowballTarget.Policy.Beta.mean": {
"value": 5.148353333333336e-05,
"min": 5.148353333333336e-05,
"max": 0.0049549902,
"count": 60
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.00020593413333333345,
"min": 0.00020593413333333345,
"max": 0.024363276,
"count": 60
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 60
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 8756.0,
"min": 8756.0,
"max": 10945.0,
"count": 60
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 27.25,
"min": 3.4318181818181817,
"max": 27.5,
"count": 60
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1199.0,
"min": 151.0,
"max": 1503.0,
"count": 60
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 27.25,
"min": 3.4318181818181817,
"max": 27.5,
"count": 60
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1199.0,
"min": 151.0,
"max": 1503.0,
"count": 60
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 60
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 60
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1766030709",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"command_line_arguments": "/usr/local/miniconda/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": "1766031820"
},
"total": 1110.774269579,
"count": 1,
"self": 0.3213235519999671,
"children": {
"run_training.setup": {
"total": 0.023646379999945566,
"count": 1,
"self": 0.023646379999945566
},
"TrainerController.start_learning": {
"total": 1110.429299647,
"count": 1,
"self": 0.9763600580206457,
"children": {
"TrainerController._reset_env": {
"total": 2.120414148000009,
"count": 1,
"self": 2.120414148000009
},
"TrainerController.advance": {
"total": 1107.2533921289794,
"count": 54592,
"self": 1.0137458358908589,
"children": {
"env_step": {
"total": 767.19922861704,
"count": 54592,
"self": 576.3346969139643,
"children": {
"SubprocessEnvManager._take_step": {
"total": 190.29560728504907,
"count": 54592,
"self": 3.3630650020234043,
"children": {
"TorchPolicy.evaluate": {
"total": 186.93254228302567,
"count": 54592,
"self": 186.93254228302567
}
}
},
"workers": {
"total": 0.5689244180266542,
"count": 54592,
"self": 0.0,
"children": {
"worker_root": {
"total": 1108.4508843770273,
"count": 54592,
"is_parallel": true,
"self": 598.6415090939877,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0019512470000790927,
"count": 1,
"is_parallel": true,
"self": 0.000606071999982305,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013451750000967877,
"count": 10,
"is_parallel": true,
"self": 0.0013451750000967877
}
}
},
"UnityEnvironment.step": {
"total": 0.026500453999915408,
"count": 1,
"is_parallel": true,
"self": 0.00037092799971105705,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00026386900003672054,
"count": 1,
"is_parallel": true,
"self": 0.00026386900003672054
},
"communicator.exchange": {
"total": 0.024662231000093016,
"count": 1,
"is_parallel": true,
"self": 0.024662231000093016
},
"steps_from_proto": {
"total": 0.0012034260000746144,
"count": 1,
"is_parallel": true,
"self": 0.00024507199964318716,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0009583540004314273,
"count": 10,
"is_parallel": true,
"self": 0.0009583540004314273
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 509.80937528303957,
"count": 54591,
"is_parallel": true,
"self": 17.981948479047787,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 9.824011489986106,
"count": 54591,
"is_parallel": true,
"self": 9.824011489986106
},
"communicator.exchange": {
"total": 423.8103065259404,
"count": 54591,
"is_parallel": true,
"self": 423.8103065259404
},
"steps_from_proto": {
"total": 58.193108788065274,
"count": 54591,
"is_parallel": true,
"self": 11.005173806939865,
"children": {
"_process_rank_one_or_two_observation": {
"total": 47.18793498112541,
"count": 545910,
"is_parallel": true,
"self": 47.18793498112541
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 339.0404176760485,
"count": 54592,
"self": 1.187494191052565,
"children": {
"process_trajectory": {
"total": 72.6635454419984,
"count": 54592,
"self": 71.57742735799934,
"children": {
"RLTrainer._checkpoint": {
"total": 1.0861180839990539,
"count": 12,
"self": 1.0861180839990539
}
}
},
"_update_policy": {
"total": 265.18937804299753,
"count": 272,
"self": 107.21645913701423,
"children": {
"TorchPPOOptimizer.update": {
"total": 157.9729189059833,
"count": 13869,
"self": 157.9729189059833
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.032999989547534e-06,
"count": 1,
"self": 1.032999989547534e-06
},
"TrainerController._save_models": {
"total": 0.07913227900007769,
"count": 1,
"self": 0.0007121559997358418,
"children": {
"RLTrainer._checkpoint": {
"total": 0.07842012300034185,
"count": 1,
"self": 0.07842012300034185
}
}
}
}
}
}
}