lacknerm's picture
First Push
bc72d3e verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.0619109869003296,
"min": 1.0619109869003296,
"max": 2.8677892684936523,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 10150.8076171875,
"min": 10150.8076171875,
"max": 29369.029296875,
"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": 12.64062213897705,
"min": 0.2935273349285126,
"max": 12.64062213897705,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2464.92138671875,
"min": 56.944305419921875,
"max": 2537.650390625,
"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.Losses.PolicyLoss.mean": {
"value": 0.06601832802841148,
"min": 0.06157643767593411,
"max": 0.07346200171010493,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.26407331211364593,
"min": 0.25728688072630057,
"max": 0.363817350795109,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.2033639948303793,
"min": 0.12843208267198256,
"max": 0.26037505429749397,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8134559793215173,
"min": 0.5137283306879302,
"max": 1.2947139815956938,
"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.CumulativeReward.mean": {
"value": 25.204545454545453,
"min": 3.590909090909091,
"max": 25.204545454545453,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1109.0,
"min": 158.0,
"max": 1359.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.204545454545453,
"min": 3.590909090909091,
"max": 25.204545454545453,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1109.0,
"min": 158.0,
"max": 1359.0,
"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": "1713435124",
"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": "2.2.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1713435556"
},
"total": 432.343341149,
"count": 1,
"self": 0.44892959700007395,
"children": {
"run_training.setup": {
"total": 0.05742661900001167,
"count": 1,
"self": 0.05742661900001167
},
"TrainerController.start_learning": {
"total": 431.83698493299994,
"count": 1,
"self": 0.5269423930060384,
"children": {
"TrainerController._reset_env": {
"total": 2.8559457349999775,
"count": 1,
"self": 2.8559457349999775
},
"TrainerController.advance": {
"total": 428.33949041799383,
"count": 18206,
"self": 0.2534813660013242,
"children": {
"env_step": {
"total": 428.0860090519925,
"count": 18206,
"self": 274.5741450440056,
"children": {
"SubprocessEnvManager._take_step": {
"total": 153.2406682259906,
"count": 18206,
"self": 1.4046249349939899,
"children": {
"TorchPolicy.evaluate": {
"total": 151.8360432909966,
"count": 18206,
"self": 151.8360432909966
}
}
},
"workers": {
"total": 0.2711957819963118,
"count": 18206,
"self": 0.0,
"children": {
"worker_root": {
"total": 430.7338534270028,
"count": 18206,
"is_parallel": true,
"self": 216.3324208069996,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.008697200000028715,
"count": 1,
"is_parallel": true,
"self": 0.004283539999846653,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0044136600001820625,
"count": 10,
"is_parallel": true,
"self": 0.0044136600001820625
}
}
},
"UnityEnvironment.step": {
"total": 0.03909450699995887,
"count": 1,
"is_parallel": true,
"self": 0.0006864109999469292,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004070219999903202,
"count": 1,
"is_parallel": true,
"self": 0.0004070219999903202
},
"communicator.exchange": {
"total": 0.035954060999983994,
"count": 1,
"is_parallel": true,
"self": 0.035954060999983994
},
"steps_from_proto": {
"total": 0.002047013000037623,
"count": 1,
"is_parallel": true,
"self": 0.00044602199989185465,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016009910001457683,
"count": 10,
"is_parallel": true,
"self": 0.0016009910001457683
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 214.40143262000322,
"count": 18205,
"is_parallel": true,
"self": 9.863213198983999,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.118601055006707,
"count": 18205,
"is_parallel": true,
"self": 5.118601055006707
},
"communicator.exchange": {
"total": 167.24098863600568,
"count": 18205,
"is_parallel": true,
"self": 167.24098863600568
},
"steps_from_proto": {
"total": 32.17862973000683,
"count": 18205,
"is_parallel": true,
"self": 6.007249677016262,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.17138005299057,
"count": 182050,
"is_parallel": true,
"self": 26.17138005299057
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00018994900005964155,
"count": 1,
"self": 0.00018994900005964155,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 423.1656860190319,
"count": 648557,
"is_parallel": true,
"self": 13.474042797059269,
"children": {
"process_trajectory": {
"total": 232.4629091709727,
"count": 648557,
"is_parallel": true,
"self": 231.51073309397282,
"children": {
"RLTrainer._checkpoint": {
"total": 0.9521760769998764,
"count": 4,
"is_parallel": true,
"self": 0.9521760769998764
}
}
},
"_update_policy": {
"total": 177.22873405099995,
"count": 90,
"is_parallel": true,
"self": 52.46857942899828,
"children": {
"TorchPPOOptimizer.update": {
"total": 124.76015462200166,
"count": 4587,
"is_parallel": true,
"self": 124.76015462200166
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.11441643800003476,
"count": 1,
"self": 0.0009284750000233544,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1134879630000114,
"count": 1,
"self": 0.1134879630000114
}
}
}
}
}
}
}