jcorblaz's picture
First Push
18db0fc verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8418481945991516,
"min": 0.8418481945991516,
"max": 2.874738931655884,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8000.92529296875,
"min": 8000.92529296875,
"max": 29345.333984375,
"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": 12.685463905334473,
"min": 0.2699587643146515,
"max": 12.685463905334473,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2473.66552734375,
"min": 52.37199783325195,
"max": 2544.912353515625,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06517658290335127,
"min": 0.06098992239675877,
"max": 0.07318057975128028,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.26070633161340506,
"min": 0.24395968958703507,
"max": 0.35147258799264036,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.21994881719058637,
"min": 0.11556570105797923,
"max": 0.2848553876082102,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8797952687623455,
"min": 0.4622628042319169,
"max": 1.4242769380410512,
"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": 24.954545454545453,
"min": 3.6136363636363638,
"max": 25.0,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1098.0,
"min": 159.0,
"max": 1353.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.954545454545453,
"min": 3.6136363636363638,
"max": 25.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1098.0,
"min": 159.0,
"max": 1353.0,
"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": "1747144349",
"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": "1747144911"
},
"total": 561.9631407319998,
"count": 1,
"self": 0.5441149239995866,
"children": {
"run_training.setup": {
"total": 0.04365536700015582,
"count": 1,
"self": 0.04365536700015582
},
"TrainerController.start_learning": {
"total": 561.3753704410001,
"count": 1,
"self": 0.6653756759860698,
"children": {
"TrainerController._reset_env": {
"total": 4.769543330000033,
"count": 1,
"self": 4.769543330000033
},
"TrainerController.advance": {
"total": 555.8628852620145,
"count": 18192,
"self": 0.6697935250422233,
"children": {
"env_step": {
"total": 389.0965711669828,
"count": 18192,
"self": 330.7745693349366,
"children": {
"SubprocessEnvManager._take_step": {
"total": 57.95707275301538,
"count": 18192,
"self": 2.056731819014658,
"children": {
"TorchPolicy.evaluate": {
"total": 55.900340934000724,
"count": 18192,
"self": 55.900340934000724
}
}
},
"workers": {
"total": 0.36492907903084415,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 559.2396415950329,
"count": 18192,
"is_parallel": true,
"self": 274.28624828201873,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.007760433999919769,
"count": 1,
"is_parallel": true,
"self": 0.005146322001110093,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002614111998809676,
"count": 10,
"is_parallel": true,
"self": 0.002614111998809676
}
}
},
"UnityEnvironment.step": {
"total": 0.05048650699973223,
"count": 1,
"is_parallel": true,
"self": 0.000794120999671577,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004911579999316018,
"count": 1,
"is_parallel": true,
"self": 0.0004911579999316018
},
"communicator.exchange": {
"total": 0.04675564999979542,
"count": 1,
"is_parallel": true,
"self": 0.04675564999979542
},
"steps_from_proto": {
"total": 0.002445578000333626,
"count": 1,
"is_parallel": true,
"self": 0.0004463400000531692,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0019992380002804566,
"count": 10,
"is_parallel": true,
"self": 0.0019992380002804566
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 284.9533933130142,
"count": 18191,
"is_parallel": true,
"self": 14.19945810408899,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 7.806530441972427,
"count": 18191,
"is_parallel": true,
"self": 7.806530441972427
},
"communicator.exchange": {
"total": 221.27889404995813,
"count": 18191,
"is_parallel": true,
"self": 221.27889404995813
},
"steps_from_proto": {
"total": 41.66851071699466,
"count": 18191,
"is_parallel": true,
"self": 8.138832899070621,
"children": {
"_process_rank_one_or_two_observation": {
"total": 33.52967781792404,
"count": 181910,
"is_parallel": true,
"self": 33.52967781792404
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 166.09652056998948,
"count": 18192,
"self": 0.8663695169661878,
"children": {
"process_trajectory": {
"total": 31.44466267702228,
"count": 18192,
"self": 30.96239675302286,
"children": {
"RLTrainer._checkpoint": {
"total": 0.4822659239994209,
"count": 4,
"self": 0.4822659239994209
}
}
},
"_update_policy": {
"total": 133.785488376001,
"count": 90,
"self": 49.93358054897408,
"children": {
"TorchPPOOptimizer.update": {
"total": 83.85190782702693,
"count": 4587,
"self": 83.85190782702693
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.1149995771120302e-06,
"count": 1,
"self": 1.1149995771120302e-06
},
"TrainerController._save_models": {
"total": 0.077565057999891,
"count": 1,
"self": 0.0011674229999698582,
"children": {
"RLTrainer._checkpoint": {
"total": 0.07639763499992114,
"count": 1,
"self": 0.07639763499992114
}
}
}
}
}
}
}