{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.970323383808136, "min": 0.970323383808136, "max": 2.863868236541748, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9275.3212890625, "min": 9275.3212890625, "max": 29328.875, "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": 12.711305618286133, "min": 0.4939640462398529, "max": 12.711305618286133, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2478.70458984375, "min": 95.82902526855469, "max": 2586.662109375, "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": 0.06984360290944631, "min": 0.06292664718896371, "max": 0.07459098086943484, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.27937441163778526, "min": 0.2633975813948257, "max": 0.3729549043471742, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20496392264670016, "min": 0.12650878262459575, "max": 0.3102169686234465, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8198556905868006, "min": 0.506035130498383, "max": 1.448567672979598, "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": 24.977272727272727, "min": 3.5681818181818183, "max": 25.345454545454544, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1099.0, "min": 157.0, "max": 1394.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.977272727272727, "min": 3.5681818181818183, "max": 25.345454545454544, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1099.0, "min": 157.0, "max": 1394.0, "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": "1688725252", "python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [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=SnowballTarget1 --no-graphics", "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": "1688725705" }, "total": 453.5441636360001, "count": 1, "self": 0.38103646900026433, "children": { "run_training.setup": { "total": 0.06683600399992429, "count": 1, "self": 0.06683600399992429 }, "TrainerController.start_learning": { "total": 453.09629116299993, "count": 1, "self": 0.4991713930093056, "children": { "TrainerController._reset_env": { "total": 5.329416342000059, "count": 1, "self": 5.329416342000059 }, "TrainerController.advance": { "total": 447.1267883439906, "count": 18202, "self": 0.24989027998583424, "children": { "env_step": { "total": 446.87689806400476, "count": 18202, "self": 324.70396985500975, "children": { "SubprocessEnvManager._take_step": { "total": 121.91878534200748, "count": 18202, "self": 1.760173510999607, "children": { "TorchPolicy.evaluate": { "total": 120.15861183100787, "count": 18202, "self": 120.15861183100787 } } }, "workers": { "total": 0.25414286698753585, "count": 18202, "self": 0.0, "children": { "worker_root": { "total": 451.5573366899936, "count": 18202, "is_parallel": true, "self": 214.86843517998136, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0059232660000816395, "count": 1, "is_parallel": true, "self": 0.0036025549999294526, "children": { "_process_rank_one_or_two_observation": { "total": 0.002320711000152187, "count": 10, "is_parallel": true, "self": 0.002320711000152187 } } }, "UnityEnvironment.step": { "total": 0.03501252099999874, "count": 1, "is_parallel": true, "self": 0.0006429580000713031, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003502029999253864, "count": 1, "is_parallel": true, "self": 0.0003502029999253864 }, "communicator.exchange": { "total": 0.03187077699999463, "count": 1, "is_parallel": true, "self": 0.03187077699999463 }, "steps_from_proto": { "total": 0.00214858300000742, "count": 1, "is_parallel": true, "self": 0.00037810699996043695, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017704760000469832, "count": 10, "is_parallel": true, "self": 0.0017704760000469832 } } } } } } }, "UnityEnvironment.step": { "total": 236.68890151001222, "count": 18201, "is_parallel": true, "self": 10.280643215037799, "children": { "UnityEnvironment._generate_step_input": { "total": 5.05909824297737, "count": 18201, "is_parallel": true, "self": 5.05909824297737 }, "communicator.exchange": { "total": 186.9428715830029, "count": 18201, "is_parallel": true, "self": 186.9428715830029 }, "steps_from_proto": { "total": 34.40628846899415, "count": 18201, "is_parallel": true, "self": 6.0606486830070025, "children": { "_process_rank_one_or_two_observation": { "total": 28.345639785987146, "count": 182010, "is_parallel": true, "self": 28.345639785987146 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00011083699996561336, "count": 1, "self": 0.00011083699996561336, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 443.8149569549498, "count": 422531, "is_parallel": true, "self": 8.884431502925736, "children": { "process_trajectory": { "total": 240.92689930202323, "count": 422531, "is_parallel": true, "self": 240.10401834902336, "children": { "RLTrainer._checkpoint": { "total": 0.8228809529998671, "count": 4, "is_parallel": true, "self": 0.8228809529998671 } } }, "_update_policy": { "total": 194.00362615000085, "count": 90, "is_parallel": true, "self": 77.68920791300081, "children": { "TorchPPOOptimizer.update": { "total": 116.31441823700004, "count": 4587, "is_parallel": true, "self": 116.31441823700004 } } } } } } } } }, "TrainerController._save_models": { "total": 0.1408042470000055, "count": 1, "self": 0.0009230649998244189, "children": { "RLTrainer._checkpoint": { "total": 0.13988118200018107, "count": 1, "self": 0.13988118200018107 } } } } } } }