was1002's picture
First Push
d1d206a verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.3348662853240967,
"min": 1.3348662853240967,
"max": 2.855766534805298,
"count": 10
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 13743.783203125,
"min": 13468.3203125,
"max": 29151.6640625,
"count": 10
},
"SnowballTarget.Step.mean": {
"value": 99960.0,
"min": 9952.0,
"max": 99960.0,
"count": 10
},
"SnowballTarget.Step.sum": {
"value": 99960.0,
"min": 9952.0,
"max": 99960.0,
"count": 10
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.2543270587921143,
"min": 0.17136120796203613,
"max": 2.2543270587921143,
"count": 10
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 459.8827209472656,
"min": 33.244075775146484,
"max": 459.8827209472656,
"count": 10
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.07471000031173211,
"min": 0.06550403799694465,
"max": 0.07471000031173211,
"count": 10
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.3735500015586606,
"min": 0.2620161519877786,
"max": 0.3735500015586606,
"count": 10
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.14008631481259476,
"min": 0.07526221758384696,
"max": 0.15946379490927157,
"count": 10
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7004315740629738,
"min": 0.30104887033538785,
"max": 0.7973189745463578,
"count": 10
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 2.7440094512e-05,
"min": 2.7440094512e-05,
"max": 0.00047294000541199993,
"count": 10
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 0.00013720047256,
"min": 0.00013720047256,
"max": 0.0021172000765599993,
"count": 10
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.105488,
"min": 0.105488,
"max": 0.194588,
"count": 10
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.52744,
"min": 0.4615520000000001,
"max": 0.92344,
"count": 10
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.0002838512,
"min": 0.0002838512,
"max": 0.0047299412,
"count": 10
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.001419256,
"min": 0.001419256,
"max": 0.021179656,
"count": 10
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 10
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 8756.0,
"max": 10945.0,
"count": 10
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 22.854545454545455,
"min": 3.590909090909091,
"max": 22.854545454545455,
"count": 10
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1257.0,
"min": 158.0,
"max": 1257.0,
"count": 10
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 22.854545454545455,
"min": 3.590909090909091,
"max": 22.854545454545455,
"count": 10
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1257.0,
"min": 158.0,
"max": 1257.0,
"count": 10
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 10
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 10
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1748106346",
"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": "2.7.0+cu126",
"numpy_version": "1.23.5",
"end_time_seconds": "1748106611"
},
"total": 265.3902492169999,
"count": 1,
"self": 0.5426437649998661,
"children": {
"run_training.setup": {
"total": 0.03905916700000489,
"count": 1,
"self": 0.03905916700000489
},
"TrainerController.start_learning": {
"total": 264.80854628500003,
"count": 1,
"self": 0.3085296310008516,
"children": {
"TrainerController._reset_env": {
"total": 3.943710390000092,
"count": 1,
"self": 3.943710390000092
},
"TrainerController.advance": {
"total": 260.48545812399914,
"count": 9128,
"self": 0.3261300299921004,
"children": {
"env_step": {
"total": 190.15306200800524,
"count": 9128,
"self": 161.99963756098975,
"children": {
"SubprocessEnvManager._take_step": {
"total": 27.97758420301193,
"count": 9128,
"self": 0.9719652530084204,
"children": {
"TorchPolicy.evaluate": {
"total": 27.00561895000351,
"count": 9128,
"self": 27.00561895000351
}
}
},
"workers": {
"total": 0.17584024400355247,
"count": 9128,
"self": 0.0,
"children": {
"worker_root": {
"total": 263.7146869450037,
"count": 9128,
"is_parallel": true,
"self": 123.70895948100394,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.008260597000003145,
"count": 1,
"is_parallel": true,
"self": 0.004959034999956202,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0033015620000469426,
"count": 10,
"is_parallel": true,
"self": 0.0033015620000469426
}
}
},
"UnityEnvironment.step": {
"total": 0.04723821200002476,
"count": 1,
"is_parallel": true,
"self": 0.0007440659999247146,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00045768500001486245,
"count": 1,
"is_parallel": true,
"self": 0.00045768500001486245
},
"communicator.exchange": {
"total": 0.043658315000016046,
"count": 1,
"is_parallel": true,
"self": 0.043658315000016046
},
"steps_from_proto": {
"total": 0.002378146000069137,
"count": 1,
"is_parallel": true,
"self": 0.0004270010000482216,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0019511450000209152,
"count": 10,
"is_parallel": true,
"self": 0.0019511450000209152
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 140.00572746399973,
"count": 9127,
"is_parallel": true,
"self": 6.866119702988385,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 3.671133970000028,
"count": 9127,
"is_parallel": true,
"self": 3.671133970000028
},
"communicator.exchange": {
"total": 108.91857460100437,
"count": 9127,
"is_parallel": true,
"self": 108.91857460100437
},
"steps_from_proto": {
"total": 20.549899190006954,
"count": 9127,
"is_parallel": true,
"self": 3.9529020300137745,
"children": {
"_process_rank_one_or_two_observation": {
"total": 16.59699715999318,
"count": 91270,
"is_parallel": true,
"self": 16.59699715999318
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 70.0062660860018,
"count": 9128,
"self": 0.4061570159975645,
"children": {
"process_trajectory": {
"total": 15.145070019004947,
"count": 9128,
"self": 14.668611388004933,
"children": {
"RLTrainer._checkpoint": {
"total": 0.47645863100001407,
"count": 5,
"self": 0.47645863100001407
}
}
},
"_update_policy": {
"total": 54.45503905099929,
"count": 45,
"self": 24.51257069899384,
"children": {
"TorchPPOOptimizer.update": {
"total": 29.94246835200545,
"count": 2292,
"self": 29.94246835200545
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.053000005413196e-06,
"count": 1,
"self": 1.053000005413196e-06
},
"TrainerController._save_models": {
"total": 0.07084708699994735,
"count": 1,
"self": 0.0009191950000513316,
"children": {
"RLTrainer._checkpoint": {
"total": 0.06992789199989602,
"count": 1,
"self": 0.06992789199989602
}
}
}
}
}
}
}