snowball-agent / run_logs /timers.json
zostrich's picture
initial release
61d4a55
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.0127224922180176,
"min": 1.0127224922180176,
"max": 2.8625142574310303,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9669.474609375,
"min": 9669.474609375,
"max": 29346.49609375,
"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": 12.520039558410645,
"min": 0.2702237069606781,
"max": 12.520039558410645,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2441.40771484375,
"min": 52.423397064208984,
"max": 2539.686767578125,
"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": 0.0615153897889803,
"min": 0.0615153897889803,
"max": 0.07635859948298757,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2460615591559212,
"min": 0.2460615591559212,
"max": 0.3577248900592346,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20357332057228275,
"min": 0.14130637424600803,
"max": 0.27932102985534013,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.814293282289131,
"min": 0.5652254969840321,
"max": 1.3196669185862822,
"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": 24.90909090909091,
"min": 3.977272727272727,
"max": 24.90909090909091,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1096.0,
"min": 175.0,
"max": 1341.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.90909090909091,
"min": 3.977272727272727,
"max": 24.90909090909091,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1096.0,
"min": 175.0,
"max": 1341.0,
"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": "1701451032",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn /content/ml-agents/config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget_initial --no-graphics",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.1.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1701451545"
},
"total": 512.843774035,
"count": 1,
"self": 0.445765634000054,
"children": {
"run_training.setup": {
"total": 0.0548156189997826,
"count": 1,
"self": 0.0548156189997826
},
"TrainerController.start_learning": {
"total": 512.3431927820002,
"count": 1,
"self": 0.6145434089394257,
"children": {
"TrainerController._reset_env": {
"total": 2.8040030309998656,
"count": 1,
"self": 2.8040030309998656
},
"TrainerController.advance": {
"total": 508.83246340306096,
"count": 18200,
"self": 0.2982819710282456,
"children": {
"env_step": {
"total": 508.5341814320327,
"count": 18200,
"self": 346.6783836740419,
"children": {
"SubprocessEnvManager._take_step": {
"total": 161.5404679280009,
"count": 18200,
"self": 1.5631175969979267,
"children": {
"TorchPolicy.evaluate": {
"total": 159.97735033100298,
"count": 18200,
"self": 159.97735033100298
}
}
},
"workers": {
"total": 0.3153298299898779,
"count": 18200,
"self": 0.0,
"children": {
"worker_root": {
"total": 511.00744123506456,
"count": 18200,
"is_parallel": true,
"self": 250.1866793500899,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0022276560002865153,
"count": 1,
"is_parallel": true,
"self": 0.0006695470015074534,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001558108998779062,
"count": 10,
"is_parallel": true,
"self": 0.001558108998779062
}
}
},
"UnityEnvironment.step": {
"total": 0.05680682199999865,
"count": 1,
"is_parallel": true,
"self": 0.0006188709994603414,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004426370001056057,
"count": 1,
"is_parallel": true,
"self": 0.0004426370001056057
},
"communicator.exchange": {
"total": 0.05392628200024774,
"count": 1,
"is_parallel": true,
"self": 0.05392628200024774
},
"steps_from_proto": {
"total": 0.0018190320001849614,
"count": 1,
"is_parallel": true,
"self": 0.0004026280003017746,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014164039998831868,
"count": 10,
"is_parallel": true,
"self": 0.0014164039998831868
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 260.8207618849747,
"count": 18199,
"is_parallel": true,
"self": 11.322517104002145,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.925261280036011,
"count": 18199,
"is_parallel": true,
"self": 5.925261280036011
},
"communicator.exchange": {
"total": 205.47443635799254,
"count": 18199,
"is_parallel": true,
"self": 205.47443635799254
},
"steps_from_proto": {
"total": 38.09854714294397,
"count": 18199,
"is_parallel": true,
"self": 7.259273905023292,
"children": {
"_process_rank_one_or_two_observation": {
"total": 30.83927323792068,
"count": 181990,
"is_parallel": true,
"self": 30.83927323792068
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00012942900002599345,
"count": 1,
"self": 0.00012942900002599345,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 504.1151917228467,
"count": 527405,
"is_parallel": true,
"self": 12.356620997098616,
"children": {
"process_trajectory": {
"total": 283.53563107074615,
"count": 527405,
"is_parallel": true,
"self": 282.842950772746,
"children": {
"RLTrainer._checkpoint": {
"total": 0.6926802980001412,
"count": 4,
"is_parallel": true,
"self": 0.6926802980001412
}
}
},
"_update_policy": {
"total": 208.22293965500194,
"count": 90,
"is_parallel": true,
"self": 67.05538467100087,
"children": {
"TorchPPOOptimizer.update": {
"total": 141.16755498400107,
"count": 4587,
"is_parallel": true,
"self": 141.16755498400107
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.09205350999991424,
"count": 1,
"self": 0.0008963759996731824,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09115713400024106,
"count": 1,
"self": 0.09115713400024106
}
}
}
}
}
}
}