zimmad's picture
First Push
3980b09 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8647057414054871,
"min": 0.8647057414054871,
"max": 2.8463265895843506,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8218.1630859375,
"min": 8218.1630859375,
"max": 29055.302734375,
"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": 13.054827690124512,
"min": 0.300916463136673,
"max": 13.054827690124512,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2545.69140625,
"min": 58.37779235839844,
"max": 2643.8330078125,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06787268036985587,
"min": 0.06337128452233076,
"max": 0.07587557180251643,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2714907214794235,
"min": 0.25700994104765557,
"max": 0.36969305406919195,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19151207275104287,
"min": 0.11898786856966348,
"max": 0.31403972167594757,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7660482910041715,
"min": 0.4759514742786539,
"max": 1.570198608379738,
"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": 26.045454545454547,
"min": 3.25,
"max": 26.045454545454547,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1146.0,
"min": 143.0,
"max": 1399.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 26.045454545454547,
"min": 3.25,
"max": 26.045454545454547,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1146.0,
"min": 143.0,
"max": 1399.0,
"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": "1771814514",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"command_line_arguments": "/usr/local/envs/mlagents_env/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": "1771814959"
},
"total": 445.45888270299974,
"count": 1,
"self": 0.5364339359998667,
"children": {
"run_training.setup": {
"total": 0.021812637000039103,
"count": 1,
"self": 0.021812637000039103
},
"TrainerController.start_learning": {
"total": 444.90063612999984,
"count": 1,
"self": 0.37447652201171877,
"children": {
"TrainerController._reset_env": {
"total": 2.7227942730000905,
"count": 1,
"self": 2.7227942730000905
},
"TrainerController.advance": {
"total": 441.72501312998793,
"count": 18192,
"self": 0.3800496489707257,
"children": {
"env_step": {
"total": 321.94613937704435,
"count": 18192,
"self": 251.72059861002208,
"children": {
"SubprocessEnvManager._take_step": {
"total": 70.00902655600657,
"count": 18192,
"self": 1.2580547080069664,
"children": {
"TorchPolicy.evaluate": {
"total": 68.75097184799961,
"count": 18192,
"self": 68.75097184799961
}
}
},
"workers": {
"total": 0.21651421101569213,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 443.0802255409908,
"count": 18192,
"is_parallel": true,
"self": 221.71735671598844,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005346563999864884,
"count": 1,
"is_parallel": true,
"self": 0.003673056000025099,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001673507999839785,
"count": 10,
"is_parallel": true,
"self": 0.001673507999839785
}
}
},
"UnityEnvironment.step": {
"total": 0.0375543039999684,
"count": 1,
"is_parallel": true,
"self": 0.0006169449998196797,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00040090899983624695,
"count": 1,
"is_parallel": true,
"self": 0.00040090899983624695
},
"communicator.exchange": {
"total": 0.03458264100027009,
"count": 1,
"is_parallel": true,
"self": 0.03458264100027009
},
"steps_from_proto": {
"total": 0.0019538090000423836,
"count": 1,
"is_parallel": true,
"self": 0.0003755589996217168,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015782500004206668,
"count": 10,
"is_parallel": true,
"self": 0.0015782500004206668
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 221.36286882500235,
"count": 18191,
"is_parallel": true,
"self": 10.406265708001229,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.675302572961755,
"count": 18191,
"is_parallel": true,
"self": 5.675302572961755
},
"communicator.exchange": {
"total": 168.15602048204255,
"count": 18191,
"is_parallel": true,
"self": 168.15602048204255
},
"steps_from_proto": {
"total": 37.12528006199682,
"count": 18191,
"is_parallel": true,
"self": 6.744350977975046,
"children": {
"_process_rank_one_or_two_observation": {
"total": 30.380929084021773,
"count": 181910,
"is_parallel": true,
"self": 30.380929084021773
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 119.39882410397286,
"count": 18192,
"self": 0.4314402789691485,
"children": {
"process_trajectory": {
"total": 26.656917064003665,
"count": 18192,
"self": 26.21801711900389,
"children": {
"RLTrainer._checkpoint": {
"total": 0.43889994499977547,
"count": 4,
"self": 0.43889994499977547
}
}
},
"_update_policy": {
"total": 92.31046676100004,
"count": 90,
"self": 37.74653169999101,
"children": {
"TorchPPOOptimizer.update": {
"total": 54.56393506100903,
"count": 4587,
"self": 54.56393506100903
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.76000137598021e-07,
"count": 1,
"self": 9.76000137598021e-07
},
"TrainerController._save_models": {
"total": 0.0783512289999635,
"count": 1,
"self": 0.0006785589998798969,
"children": {
"RLTrainer._checkpoint": {
"total": 0.0776726700000836,
"count": 1,
"self": 0.0776726700000836
}
}
}
}
}
}
}