Alex48's picture
Second train of SnowballTarget
0a62d45
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8241392374038696,
"min": 0.8241392374038696,
"max": 2.8787403106689453,
"count": 40
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8421.87890625,
"min": 7984.82763671875,
"max": 29797.83984375,
"count": 40
},
"SnowballTarget.Step.mean": {
"value": 399992.0,
"min": 9952.0,
"max": 399992.0,
"count": 40
},
"SnowballTarget.Step.sum": {
"value": 399992.0,
"min": 9952.0,
"max": 399992.0,
"count": 40
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 13.510470390319824,
"min": 0.09209876507520676,
"max": 13.556648254394531,
"count": 40
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2634.541748046875,
"min": 17.86716079711914,
"max": 2770.59130859375,
"count": 40
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 40
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 8756.0,
"min": 8756.0,
"max": 10945.0,
"count": 40
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 26.65909090909091,
"min": 2.8863636363636362,
"max": 26.88888888888889,
"count": 40
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1173.0,
"min": 127.0,
"max": 1453.0,
"count": 40
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 26.65909090909091,
"min": 2.8863636363636362,
"max": 26.88888888888889,
"count": 40
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1173.0,
"min": 127.0,
"max": 1453.0,
"count": 40
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.04546067557941355,
"min": 0.042070891773387395,
"max": 0.05577735437933977,
"count": 40
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.0909213511588271,
"min": 0.08414178354677479,
"max": 0.1583393368705669,
"count": 40
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.15301765158188108,
"min": 0.09006862982185375,
"max": 0.31951044134649575,
"count": 40
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.30603530316376215,
"min": 0.1801372596437075,
"max": 0.8356520559857874,
"count": 40
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 4.716098428000004e-06,
"min": 4.716098428000004e-06,
"max": 0.000295116001628,
"count": 40
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 9.432196856000007e-06,
"min": 9.432196856000007e-06,
"max": 0.000820998026334,
"count": 40
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.101572,
"min": 0.101572,
"max": 0.198372,
"count": 40
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.203144,
"min": 0.203144,
"max": 0.5736660000000001,
"count": 40
},
"SnowballTarget.Policy.Beta.mean": {
"value": 8.844280000000006e-05,
"min": 8.844280000000006e-05,
"max": 0.004918762799999999,
"count": 40
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.00017688560000000012,
"min": 0.00017688560000000012,
"max": 0.013685933400000001,
"count": 40
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 40
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 40
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1677350865",
"python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[GCC 9.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget2 --no-graphics",
"mlagents_version": "0.29.0.dev0",
"mlagents_envs_version": "0.29.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.8.1+cu102",
"numpy_version": "1.22.4",
"end_time_seconds": "1677351763"
},
"total": 897.8772009929999,
"count": 1,
"self": 0.734729729999799,
"children": {
"run_training.setup": {
"total": 0.11248506700030703,
"count": 1,
"self": 0.11248506700030703
},
"TrainerController.start_learning": {
"total": 897.0299861959998,
"count": 1,
"self": 1.076378736015613,
"children": {
"TrainerController._reset_env": {
"total": 7.147789585999817,
"count": 1,
"self": 7.147789585999817
},
"TrainerController.advance": {
"total": 888.565351069984,
"count": 36416,
"self": 0.528692997982489,
"children": {
"env_step": {
"total": 888.0366580720015,
"count": 36416,
"self": 620.2295475150513,
"children": {
"SubprocessEnvManager._take_step": {
"total": 267.28082236993987,
"count": 36416,
"self": 3.1298786848901727,
"children": {
"TorchPolicy.evaluate": {
"total": 264.1509436850497,
"count": 36416,
"self": 56.354647853004735,
"children": {
"TorchPolicy.sample_actions": {
"total": 207.79629583204496,
"count": 36416,
"self": 207.79629583204496
}
}
}
}
},
"workers": {
"total": 0.5262881870103229,
"count": 36416,
"self": 0.0,
"children": {
"worker_root": {
"total": 893.9885211770265,
"count": 36416,
"is_parallel": true,
"self": 425.1962783910244,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0022482740000668855,
"count": 1,
"is_parallel": true,
"self": 0.000785426001129963,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014628479989369225,
"count": 10,
"is_parallel": true,
"self": 0.0014628479989369225
}
}
},
"UnityEnvironment.step": {
"total": 0.04437245400004031,
"count": 1,
"is_parallel": true,
"self": 0.0005378729997573828,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00029277700014063157,
"count": 1,
"is_parallel": true,
"self": 0.00029277700014063157
},
"communicator.exchange": {
"total": 0.041718575000231795,
"count": 1,
"is_parallel": true,
"self": 0.041718575000231795
},
"steps_from_proto": {
"total": 0.0018232289999104978,
"count": 1,
"is_parallel": true,
"self": 0.0004162840004937607,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014069449994167371,
"count": 10,
"is_parallel": true,
"self": 0.0014069449994167371
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 468.79224278600213,
"count": 36415,
"is_parallel": true,
"self": 18.68105090993322,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 10.327643597010137,
"count": 36415,
"is_parallel": true,
"self": 10.327643597010137
},
"communicator.exchange": {
"total": 378.4170795610071,
"count": 36415,
"is_parallel": true,
"self": 378.4170795610071
},
"steps_from_proto": {
"total": 61.36646871805169,
"count": 36415,
"is_parallel": true,
"self": 13.253275974245298,
"children": {
"_process_rank_one_or_two_observation": {
"total": 48.113192743806394,
"count": 364150,
"is_parallel": true,
"self": 48.113192743806394
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00021788300000480376,
"count": 1,
"self": 0.00021788300000480376,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 879.8872030884322,
"count": 1007552,
"is_parallel": true,
"self": 24.59325653447786,
"children": {
"process_trajectory": {
"total": 619.7395709079497,
"count": 1007552,
"is_parallel": true,
"self": 617.4357846219505,
"children": {
"RLTrainer._checkpoint": {
"total": 2.3037862859991947,
"count": 8,
"is_parallel": true,
"self": 2.3037862859991947
}
}
},
"_update_policy": {
"total": 235.5543756460047,
"count": 90,
"is_parallel": true,
"self": 115.87152756699288,
"children": {
"TorchPPOOptimizer.update": {
"total": 119.68284807901182,
"count": 4587,
"is_parallel": true,
"self": 119.68284807901182
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.24024892100032957,
"count": 1,
"self": 0.0022735880002073827,
"children": {
"RLTrainer._checkpoint": {
"total": 0.2379753330001222,
"count": 1,
"self": 0.2379753330001222
}
}
}
}
}
}
}