anevarela's picture
First Push
616ce5f verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.6948115825653076,
"min": 0.6774803400039673,
"max": 2.8294575214385986,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 6603.4892578125,
"min": 6603.4892578125,
"max": 28883.1015625,
"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": 11.766664505004883,
"min": 0.38761410117149353,
"max": 11.766664505004883,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2294.49951171875,
"min": 75.19713592529297,
"max": 2385.40771484375,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06153925984992882,
"min": 0.06153925984992882,
"max": 0.07826306362567623,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.24615703939971528,
"min": 0.24615703939971528,
"max": 0.3677644229473491,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19396322297261043,
"min": 0.1282996081817877,
"max": 0.2822387177570193,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7758528918904417,
"min": 0.5131984327271508,
"max": 1.4111935887850966,
"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": 22.59090909090909,
"min": 3.7954545454545454,
"max": 23.59090909090909,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 994.0,
"min": 167.0,
"max": 1287.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 22.59090909090909,
"min": 3.7954545454545454,
"max": 23.59090909090909,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 994.0,
"min": 167.0,
"max": 1287.0,
"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": "1749454845",
"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": "2.7.1+cu126",
"numpy_version": "1.23.5",
"end_time_seconds": "1749455272"
},
"total": 426.47453149499995,
"count": 1,
"self": 0.38720386599993617,
"children": {
"run_training.setup": {
"total": 0.022718827999938185,
"count": 1,
"self": 0.022718827999938185
},
"TrainerController.start_learning": {
"total": 426.0646088010001,
"count": 1,
"self": 0.33751697700643035,
"children": {
"TrainerController._reset_env": {
"total": 3.053959748000011,
"count": 1,
"self": 3.053959748000011
},
"TrainerController.advance": {
"total": 422.5771159859937,
"count": 18192,
"self": 0.38201090900702184,
"children": {
"env_step": {
"total": 301.3575947399904,
"count": 18192,
"self": 228.87181199700694,
"children": {
"SubprocessEnvManager._take_step": {
"total": 72.28637911899398,
"count": 18192,
"self": 1.253328948994863,
"children": {
"TorchPolicy.evaluate": {
"total": 71.03305016999911,
"count": 18192,
"self": 71.03305016999911
}
}
},
"workers": {
"total": 0.19940362398949674,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 424.67862669100816,
"count": 18192,
"is_parallel": true,
"self": 223.77837075501054,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005158249000032811,
"count": 1,
"is_parallel": true,
"self": 0.003651521999927354,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015067270001054567,
"count": 10,
"is_parallel": true,
"self": 0.0015067270001054567
}
}
},
"UnityEnvironment.step": {
"total": 0.03617443200005255,
"count": 1,
"is_parallel": true,
"self": 0.0005959440001106486,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003908840000121927,
"count": 1,
"is_parallel": true,
"self": 0.0003908840000121927
},
"communicator.exchange": {
"total": 0.033395742999914546,
"count": 1,
"is_parallel": true,
"self": 0.033395742999914546
},
"steps_from_proto": {
"total": 0.0017918610000151602,
"count": 1,
"is_parallel": true,
"self": 0.00038976300015747256,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014020979998576877,
"count": 10,
"is_parallel": true,
"self": 0.0014020979998576877
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 200.90025593599762,
"count": 18191,
"is_parallel": true,
"self": 9.782234260027849,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.535962885986805,
"count": 18191,
"is_parallel": true,
"self": 5.535962885986805
},
"communicator.exchange": {
"total": 153.7111484409893,
"count": 18191,
"is_parallel": true,
"self": 153.7111484409893
},
"steps_from_proto": {
"total": 31.870910348993675,
"count": 18191,
"is_parallel": true,
"self": 5.586226706988327,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.284683642005348,
"count": 181910,
"is_parallel": true,
"self": 26.284683642005348
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 120.83751033699627,
"count": 18192,
"self": 0.4271209610021742,
"children": {
"process_trajectory": {
"total": 27.351696868994395,
"count": 18192,
"self": 26.93553274999431,
"children": {
"RLTrainer._checkpoint": {
"total": 0.41616411900008643,
"count": 4,
"self": 0.41616411900008643
}
}
},
"_update_policy": {
"total": 93.0586925069997,
"count": 90,
"self": 37.43265352799892,
"children": {
"TorchPPOOptimizer.update": {
"total": 55.62603897900078,
"count": 4587,
"self": 55.62603897900078
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0199998996540671e-06,
"count": 1,
"self": 1.0199998996540671e-06
},
"TrainerController._save_models": {
"total": 0.0960150700000213,
"count": 1,
"self": 0.0008020000000215077,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09521306999999979,
"count": 1,
"self": 0.09521306999999979
}
}
}
}
}
}
}