rezadadfar's picture
First Push
b230487
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9632484316825867,
"min": 0.946694552898407,
"max": 2.831773519515991,
"count": 38
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9779.861328125,
"min": 8997.384765625,
"max": 29000.19140625,
"count": 38
},
"SnowballTarget.Step.mean": {
"value": 379936.0,
"min": 9952.0,
"max": 379936.0,
"count": 38
},
"SnowballTarget.Step.sum": {
"value": 379936.0,
"min": 9952.0,
"max": 379936.0,
"count": 38
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 9.31008243560791,
"min": 0.3737933039665222,
"max": 10.39278507232666,
"count": 38
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 1806.156005859375,
"min": 72.51589965820312,
"max": 2120.128173828125,
"count": 38
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 38
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 8756.0,
"min": 8756.0,
"max": 10945.0,
"count": 38
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.07979028274801472,
"min": 0.07011714715135182,
"max": 0.07979028274801472,
"count": 38
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.3191611309920589,
"min": 0.2804685886054073,
"max": 0.396103663790478,
"count": 38
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.15876583798112823,
"min": 0.10814841084168567,
"max": 0.26334494376445516,
"count": 38
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.6350633519245129,
"min": 0.43259364336674266,
"max": 1.2059850227599052,
"count": 38
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 0.0002437482187506,
"min": 0.0002437482187506,
"max": 0.00029918820027059994,
"count": 38
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 0.0009749928750024,
"min": 0.0009749928750024,
"max": 0.001488516003828,
"count": 38
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.1812494,
"min": 0.1812494,
"max": 0.1997294,
"count": 38
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.7249976,
"min": 0.7249976,
"max": 0.996172,
"count": 38
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.00406434506,
"min": 0.00406434506,
"max": 0.004986497059999999,
"count": 38
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.01625738024,
"min": 0.01625738024,
"max": 0.0248089828,
"count": 38
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 18.045454545454547,
"min": 3.3863636363636362,
"max": 20.85185185185185,
"count": 38
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 794.0,
"min": 149.0,
"max": 1126.0,
"count": 38
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 18.045454545454547,
"min": 3.3863636363636362,
"max": 20.85185185185185,
"count": 38
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 794.0,
"min": 149.0,
"max": 1126.0,
"count": 38
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 38
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 38
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1703981975",
"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": "1703984360"
},
"total": 2384.312653194,
"count": 1,
"self": 0.011582782000004954,
"children": {
"run_training.setup": {
"total": 0.21871392200000628,
"count": 1,
"self": 0.21871392200000628
},
"TrainerController.start_learning": {
"total": 2384.08235649,
"count": 1,
"self": 2.061458510040211,
"children": {
"TrainerController._reset_env": {
"total": 4.11586097899999,
"count": 1,
"self": 4.11586097899999
},
"TrainerController.advance": {
"total": 2377.65417228096,
"count": 34664,
"self": 0.5072621089611857,
"children": {
"env_step": {
"total": 2377.146910171999,
"count": 34664,
"self": 2093.3412678450004,
"children": {
"SubprocessEnvManager._take_step": {
"total": 283.27151357100126,
"count": 34664,
"self": 2.789369170029204,
"children": {
"TorchPolicy.evaluate": {
"total": 280.48214440097206,
"count": 34664,
"self": 280.48214440097206
}
}
},
"workers": {
"total": 0.5341287559972443,
"count": 34664,
"self": 0.0,
"children": {
"worker_root": {
"total": 2375.347796963948,
"count": 34664,
"is_parallel": true,
"self": 1928.8743105408766,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006852160999983425,
"count": 1,
"is_parallel": true,
"self": 0.004942262000326991,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0019098989996564342,
"count": 10,
"is_parallel": true,
"self": 0.0019098989996564342
}
}
},
"UnityEnvironment.step": {
"total": 0.038009821000059674,
"count": 1,
"is_parallel": true,
"self": 0.0007187859999930879,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004127219999645604,
"count": 1,
"is_parallel": true,
"self": 0.0004127219999645604
},
"communicator.exchange": {
"total": 0.03482159500003945,
"count": 1,
"is_parallel": true,
"self": 0.03482159500003945
},
"steps_from_proto": {
"total": 0.002056718000062574,
"count": 1,
"is_parallel": true,
"self": 0.00040723500023887027,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016494829998237037,
"count": 10,
"is_parallel": true,
"self": 0.0016494829998237037
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 446.47348642307145,
"count": 34663,
"is_parallel": true,
"self": 20.766465504084067,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 9.99637287499013,
"count": 34663,
"is_parallel": true,
"self": 9.99637287499013
},
"communicator.exchange": {
"total": 351.1665285129891,
"count": 34663,
"is_parallel": true,
"self": 351.1665285129891
},
"steps_from_proto": {
"total": 64.54411953100816,
"count": 34663,
"is_parallel": true,
"self": 12.063705354110539,
"children": {
"_process_rank_one_or_two_observation": {
"total": 52.480414176897625,
"count": 346630,
"is_parallel": true,
"self": 52.480414176897625
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 5.642199994326802e-05,
"count": 1,
"self": 5.642199994326802e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 2360.56398427288,
"count": 1295259,
"is_parallel": true,
"self": 26.059738177116742,
"children": {
"process_trajectory": {
"total": 480.37304893676185,
"count": 1295260,
"is_parallel": true,
"self": 478.66377789176136,
"children": {
"RLTrainer._checkpoint": {
"total": 1.7092710450004915,
"count": 7,
"is_parallel": true,
"self": 1.7092710450004915
}
}
},
"_update_policy": {
"total": 1854.1311971590014,
"count": 172,
"is_parallel": true,
"self": 790.5737451379971,
"children": {
"TorchPPOOptimizer.update": {
"total": 1063.5574520210043,
"count": 88046,
"is_parallel": true,
"self": 1063.5574520210043
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.25080829799981075,
"count": 1,
"self": 0.0016997379993881623,
"children": {
"RLTrainer._checkpoint": {
"total": 0.24910856000042259,
"count": 1,
"self": 0.24910856000042259
}
}
}
}
}
}
}