KaushikSahoo's picture
First Push
59e475f verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.7814939618110657,
"min": 0.7807473540306091,
"max": 2.859774589538574,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7427.318359375,
"min": 7427.318359375,
"max": 29192.578125,
"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": 12.689658164978027,
"min": 0.30128583312034607,
"max": 12.689658164978027,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2474.4833984375,
"min": 58.4494514465332,
"max": 2584.66845703125,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06929915102013826,
"min": 0.0621536623200347,
"max": 0.07758549751537537,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.277196604080553,
"min": 0.25686729511625006,
"max": 0.37040574498949386,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19194015725424476,
"min": 0.1075584204210078,
"max": 0.2730062421338231,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7677606290169791,
"min": 0.4302336816840312,
"max": 1.3407711041908636,
"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": 25.113636363636363,
"min": 3.477272727272727,
"max": 25.113636363636363,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1105.0,
"min": 153.0,
"max": 1377.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.113636363636363,
"min": 3.477272727272727,
"max": 25.113636363636363,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1105.0,
"min": 153.0,
"max": 1377.0,
"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": "1746722987",
"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": "1746723424"
},
"total": 437.26082896599996,
"count": 1,
"self": 0.434608647999994,
"children": {
"run_training.setup": {
"total": 0.02276593400006277,
"count": 1,
"self": 0.02276593400006277
},
"TrainerController.start_learning": {
"total": 436.8034543839999,
"count": 1,
"self": 0.3482128879868469,
"children": {
"TrainerController._reset_env": {
"total": 3.3181874019999213,
"count": 1,
"self": 3.3181874019999213
},
"TrainerController.advance": {
"total": 433.05263581201325,
"count": 18192,
"self": 0.4043727010073326,
"children": {
"env_step": {
"total": 308.72011494600645,
"count": 18192,
"self": 235.99342805101776,
"children": {
"SubprocessEnvManager._take_step": {
"total": 72.51227473998745,
"count": 18192,
"self": 1.3636355319691802,
"children": {
"TorchPolicy.evaluate": {
"total": 71.14863920801827,
"count": 18192,
"self": 71.14863920801827
}
}
},
"workers": {
"total": 0.21441215500124144,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 435.3446343900048,
"count": 18192,
"is_parallel": true,
"self": 228.74420497901997,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0051393989999724,
"count": 1,
"is_parallel": true,
"self": 0.003552335999756906,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001587063000215494,
"count": 10,
"is_parallel": true,
"self": 0.001587063000215494
}
}
},
"UnityEnvironment.step": {
"total": 0.07087883600001987,
"count": 1,
"is_parallel": true,
"self": 0.0006107820000806896,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00043387300001995754,
"count": 1,
"is_parallel": true,
"self": 0.00043387300001995754
},
"communicator.exchange": {
"total": 0.06789818300001116,
"count": 1,
"is_parallel": true,
"self": 0.06789818300001116
},
"steps_from_proto": {
"total": 0.0019359979999080679,
"count": 1,
"is_parallel": true,
"self": 0.0004817979998961164,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014542000000119515,
"count": 10,
"is_parallel": true,
"self": 0.0014542000000119515
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 206.60042941098482,
"count": 18191,
"is_parallel": true,
"self": 10.10200976195381,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.649117720000049,
"count": 18191,
"is_parallel": true,
"self": 5.649117720000049
},
"communicator.exchange": {
"total": 157.90162290901912,
"count": 18191,
"is_parallel": true,
"self": 157.90162290901912
},
"steps_from_proto": {
"total": 32.94767902001183,
"count": 18191,
"is_parallel": true,
"self": 5.994207409033834,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.953471610978,
"count": 181910,
"is_parallel": true,
"self": 26.953471610978
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 123.92814816499947,
"count": 18192,
"self": 0.4379685939729825,
"children": {
"process_trajectory": {
"total": 28.49884626602534,
"count": 18192,
"self": 28.047152300025346,
"children": {
"RLTrainer._checkpoint": {
"total": 0.45169396599999345,
"count": 4,
"self": 0.45169396599999345
}
}
},
"_update_policy": {
"total": 94.99133330500115,
"count": 90,
"self": 38.70520676300907,
"children": {
"TorchPPOOptimizer.update": {
"total": 56.286126541992076,
"count": 4587,
"self": 56.286126541992076
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.729999419505475e-07,
"count": 1,
"self": 9.729999419505475e-07
},
"TrainerController._save_models": {
"total": 0.08441730899994582,
"count": 1,
"self": 0.0008659159998387622,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08355139300010705,
"count": 1,
"self": 0.08355139300010705
}
}
}
}
}
}
}