hour3's picture
First Push
7fb5f6a
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9923916459083557,
"min": 0.48787441849708557,
"max": 2.8903489112854004,
"count": 1651
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 21.832616806030273,
"min": 6.256749629974365,
"max": 2225.563720703125,
"count": 1651
},
"SnowballTarget.Step.mean": {
"value": 200048.0,
"min": 64.0,
"max": 200048.0,
"count": 2001
},
"SnowballTarget.Step.sum": {
"value": 200048.0,
"min": 64.0,
"max": 200048.0,
"count": 2001
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 12.738629341125488,
"min": -0.00015642819926142693,
"max": 12.773412704467773,
"count": 2001
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 12.738629341125488,
"min": -0.00015642819926142693,
"max": 139.175048828125,
"count": 2001
},
"SnowballTarget.IsTraining.mean": {
"value": 0.0,
"min": 0.0,
"max": 1.0,
"count": 2001
},
"SnowballTarget.IsTraining.sum": {
"value": 0.0,
"min": 0.0,
"max": 1.0,
"count": 2001
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 90
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 2189.0,
"min": 2189.0,
"max": 2189.0,
"count": 90
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.0663354033124907,
"min": 0.05188724294067452,
"max": 0.08553984459927853,
"count": 90
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.0663354033124907,
"min": 0.05188724294067452,
"max": 0.08553984459927853,
"count": 90
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19322536067635404,
"min": 0.08837025232302646,
"max": 0.29375091808683734,
"count": 90
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.19322536067635404,
"min": 0.08837025232302646,
"max": 0.29375091808683734,
"count": 90
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 3.1320989560000013e-06,
"min": 3.1320989560000013e-06,
"max": 0.000296832001056,
"count": 90
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 3.1320989560000013e-06,
"min": 3.1320989560000013e-06,
"max": 0.000296832001056,
"count": 90
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.101044,
"min": 0.101044,
"max": 0.198944,
"count": 90
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.101044,
"min": 0.101044,
"max": 0.198944,
"count": 90
},
"SnowballTarget.Policy.Beta.mean": {
"value": 6.209560000000005e-05,
"min": 6.209560000000005e-05,
"max": 0.0049473056,
"count": 90
},
"SnowballTarget.Policy.Beta.sum": {
"value": 6.209560000000005e-05,
"min": 6.209560000000005e-05,
"max": 0.0049473056,
"count": 90
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 27.0,
"min": 1.0,
"max": 29.0,
"count": 180
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 27.0,
"min": 1.0,
"max": 260.0,
"count": 180
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 27.0,
"min": 1.0,
"max": 29.0,
"count": 180
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 27.0,
"min": 1.0,
"max": 260.0,
"count": 180
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1704031646",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
"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": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.1.2+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1704032082"
},
"total": 436.19627553299995,
"count": 1,
"self": 0.4379654209999444,
"children": {
"run_training.setup": {
"total": 0.07694842599994445,
"count": 1,
"self": 0.07694842599994445
},
"TrainerController.start_learning": {
"total": 435.68136168600006,
"count": 1,
"self": 0.5219666319933367,
"children": {
"TrainerController._reset_env": {
"total": 3.052960862999953,
"count": 1,
"self": 3.052960862999953
},
"TrainerController.advance": {
"total": 432.01761871000656,
"count": 18199,
"self": 0.2541309350000347,
"children": {
"env_step": {
"total": 431.7634877750065,
"count": 18199,
"self": 282.8951208140031,
"children": {
"SubprocessEnvManager._take_step": {
"total": 148.60470374000022,
"count": 18199,
"self": 1.410746324998513,
"children": {
"TorchPolicy.evaluate": {
"total": 147.1939574150017,
"count": 18199,
"self": 147.1939574150017
}
}
},
"workers": {
"total": 0.26366322100318484,
"count": 18199,
"self": 0.0,
"children": {
"worker_root": {
"total": 434.4567127710051,
"count": 18199,
"is_parallel": true,
"self": 215.31264107301013,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.004597649999936948,
"count": 1,
"is_parallel": true,
"self": 0.003299636999827271,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012980130001096768,
"count": 10,
"is_parallel": true,
"self": 0.0012980130001096768
}
}
},
"UnityEnvironment.step": {
"total": 0.0522200719999546,
"count": 1,
"is_parallel": true,
"self": 0.0007183440000062546,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003976119999151706,
"count": 1,
"is_parallel": true,
"self": 0.0003976119999151706
},
"communicator.exchange": {
"total": 0.049116421000007904,
"count": 1,
"is_parallel": true,
"self": 0.049116421000007904
},
"steps_from_proto": {
"total": 0.001987695000025269,
"count": 1,
"is_parallel": true,
"self": 0.0003799619998972048,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016077330001280643,
"count": 10,
"is_parallel": true,
"self": 0.0016077330001280643
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 219.14407169799495,
"count": 18198,
"is_parallel": true,
"self": 10.502013621999936,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.226737684008754,
"count": 18198,
"is_parallel": true,
"self": 5.226737684008754
},
"communicator.exchange": {
"total": 170.3621732599895,
"count": 18198,
"is_parallel": true,
"self": 170.3621732599895
},
"steps_from_proto": {
"total": 33.05314713199675,
"count": 18198,
"is_parallel": true,
"self": 6.1366368230039825,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.91651030899277,
"count": 181980,
"is_parallel": true,
"self": 26.91651030899277
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00012267600004634005,
"count": 1,
"self": 0.00012267600004634005,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 426.69530121803507,
"count": 656330,
"is_parallel": true,
"self": 13.671866556084296,
"children": {
"process_trajectory": {
"total": 237.93472173795203,
"count": 656330,
"is_parallel": true,
"self": 237.32547044895205,
"children": {
"RLTrainer._checkpoint": {
"total": 0.6092512889999853,
"count": 4,
"is_parallel": true,
"self": 0.6092512889999853
}
}
},
"_update_policy": {
"total": 175.08871292399874,
"count": 90,
"is_parallel": true,
"self": 53.93562512199685,
"children": {
"TorchPPOOptimizer.update": {
"total": 121.15308780200189,
"count": 4587,
"is_parallel": true,
"self": 121.15308780200189
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.0886928050001643,
"count": 1,
"self": 0.0009655800001837633,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08772722499998054,
"count": 1,
"self": 0.08772722499998054
}
}
}
}
}
}
}