manuu01's picture
First training
7ef4711
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9890973567962646,
"min": 0.9890973567962646,
"max": 2.460813045501709,
"count": 16
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 10042.3056640625,
"min": 9925.787109375,
"max": 25174.1171875,
"count": 16
},
"SnowballTarget.Step.mean": {
"value": 199984.0,
"min": 49936.0,
"max": 199984.0,
"count": 16
},
"SnowballTarget.Step.sum": {
"value": 199984.0,
"min": 49936.0,
"max": 199984.0,
"count": 16
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 12.787372589111328,
"min": 4.091639041900635,
"max": 12.787372589111328,
"count": 16
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2493.53759765625,
"min": 781.5030517578125,
"max": 2569.100830078125,
"count": 16
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 16
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 8756.0,
"min": 8756.0,
"max": 10945.0,
"count": 16
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06615653375343292,
"min": 0.06300088437502363,
"max": 0.07376167573730688,
"count": 16
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.26462613501373167,
"min": 0.2520035375000945,
"max": 0.36384642571005427,
"count": 16
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.2003166273820634,
"min": 0.2003166273820634,
"max": 0.2648887283661786,
"count": 16
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8012665095282536,
"min": 0.8012665095282536,
"max": 1.3244436418308931,
"count": 16
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 9.624097594000011e-06,
"min": 9.624097594000011e-06,
"max": 0.000308824022794,
"count": 16
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 3.8496390376000045e-05,
"min": 3.8496390376000045e-05,
"max": 0.00144512013872,
"count": 16
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10240600000000001,
"min": 0.10240600000000001,
"max": 0.17720600000000003,
"count": 16
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.40962400000000004,
"min": 0.40962400000000004,
"max": 0.8612800000000002,
"count": 16
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.00013005940000000016,
"min": 0.00013005940000000016,
"max": 0.0038625794000000002,
"count": 16
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0005202376000000006,
"min": 0.0005202376000000006,
"max": 0.018077872000000002,
"count": 16
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 25.65909090909091,
"min": 10.568181818181818,
"max": 25.65909090909091,
"count": 16
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1129.0,
"min": 465.0,
"max": 1389.0,
"count": 16
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.65909090909091,
"min": 10.568181818181818,
"max": 25.65909090909091,
"count": 16
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1129.0,
"min": 465.0,
"max": 1389.0,
"count": 16
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 16
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 16
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1690536120",
"python_version": "3.10.6 (main, May 29 2023, 11:10:38) [GCC 11.3.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn /content/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --resume",
"mlagents_version": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.11.0+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1690536506"
},
"total": 385.418019159,
"count": 1,
"self": 0.47516103700002077,
"children": {
"run_training.setup": {
"total": 0.05412598199995955,
"count": 1,
"self": 0.05412598199995955
},
"TrainerController.start_learning": {
"total": 384.88873214,
"count": 1,
"self": 0.686257808997766,
"children": {
"TrainerController._reset_env": {
"total": 0.9650156669999888,
"count": 1,
"self": 0.9650156669999888
},
"TrainerController.advance": {
"total": 383.12162565700226,
"count": 14597,
"self": 0.3062209929976234,
"children": {
"env_step": {
"total": 382.81540466400463,
"count": 14597,
"self": 307.8672535230055,
"children": {
"SubprocessEnvManager._take_step": {
"total": 74.64246489801292,
"count": 14597,
"self": 1.7589454060108665,
"children": {
"TorchPolicy.evaluate": {
"total": 72.88351949200205,
"count": 14597,
"self": 72.88351949200205
}
}
},
"workers": {
"total": 0.30568624298621216,
"count": 14597,
"self": 0.0,
"children": {
"worker_root": {
"total": 383.3251138129947,
"count": 14597,
"is_parallel": true,
"self": 175.30222937801136,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0014664000000266242,
"count": 1,
"is_parallel": true,
"self": 0.00037068999995426566,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0010957100000723585,
"count": 10,
"is_parallel": true,
"self": 0.0010957100000723585
}
}
},
"UnityEnvironment.step": {
"total": 0.03387123499999234,
"count": 1,
"is_parallel": true,
"self": 0.0005519200000208002,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003436599999986356,
"count": 1,
"is_parallel": true,
"self": 0.0003436599999986356
},
"communicator.exchange": {
"total": 0.03119507499991414,
"count": 1,
"is_parallel": true,
"self": 0.03119507499991414
},
"steps_from_proto": {
"total": 0.0017805800000587624,
"count": 1,
"is_parallel": true,
"self": 0.00047070999994502927,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013098700001137331,
"count": 10,
"is_parallel": true,
"self": 0.0013098700001137331
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 208.02288443498333,
"count": 14596,
"is_parallel": true,
"self": 8.164392102988927,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 4.93495916499819,
"count": 14596,
"is_parallel": true,
"self": 4.93495916499819
},
"communicator.exchange": {
"total": 169.05194805099563,
"count": 14596,
"is_parallel": true,
"self": 169.05194805099563
},
"steps_from_proto": {
"total": 25.871585116000574,
"count": 14596,
"is_parallel": true,
"self": 5.392993893981497,
"children": {
"_process_rank_one_or_two_observation": {
"total": 20.478591222019077,
"count": 145960,
"is_parallel": true,
"self": 20.478591222019077
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0006157400000574853,
"count": 1,
"self": 0.0006157400000574853,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 380.044794646994,
"count": 400173,
"is_parallel": true,
"self": 8.097505638985695,
"children": {
"process_trajectory": {
"total": 206.17336836000788,
"count": 400173,
"is_parallel": true,
"self": 198.4894372770077,
"children": {
"RLTrainer._checkpoint": {
"total": 7.683931083000175,
"count": 32,
"is_parallel": true,
"self": 7.683931083000175
}
}
},
"_update_policy": {
"total": 165.7739206480004,
"count": 72,
"is_parallel": true,
"self": 46.95509156000287,
"children": {
"TorchPPOOptimizer.update": {
"total": 118.81882908799753,
"count": 3666,
"is_parallel": true,
"self": 118.81882908799753
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.11521726699993451,
"count": 1,
"self": 0.0014005190000716539,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11381674799986286,
"count": 1,
"self": 0.11381674799986286
}
}
}
}
}
}
}