{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.6970001459121704, "min": 1.6970001459121704, "max": 2.888772487640381, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 15026.9365234375, "min": 15026.9365234375, "max": 29679.248046875, "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": 8.410125732421875, "min": 0.16790492832660675, "max": 8.410125732421875, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 1639.9744873046875, "min": 32.57355499267578, "max": 1649.48046875, "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.Environment.CumulativeReward.mean": { "value": 19.295454545454547, "min": 2.6818181818181817, "max": 19.295454545454547, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 849.0, "min": 118.0, "max": 1022.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 19.295454545454547, "min": 2.6818181818181817, "max": 19.295454545454547, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 849.0, "min": 118.0, "max": 1022.0, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.03775463946577576, "min": 0.028190646006516072, "max": 0.041376562806329245, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.03775463946577576, "min": 0.028729523391963017, "max": 0.08275312561265849, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.3312886125511593, "min": 0.09616799376629016, "max": 0.33375245415502125, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.3312886125511593, "min": 0.09616799376629016, "max": 0.6675049083100425, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 7.488097503999994e-06, "min": 7.488097503999994e-06, "max": 0.000292344002552, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 7.488097503999994e-06, "min": 7.488097503999994e-06, "max": 0.0005617200127599999, "count": 20 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10249599999999999, "min": 0.10249599999999999, "max": 0.19744799999999996, "count": 20 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.10249599999999999, "min": 0.10249599999999999, "max": 0.38724000000000003, "count": 20 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0001345503999999999, "min": 0.0001345503999999999, "max": 0.0048726552, "count": 20 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0001345503999999999, "min": 0.0001345503999999999, "max": 0.009363276, "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": "1696036172", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "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": "1696036629" }, "total": 456.8298716510001, "count": 1, "self": 0.43511942400004955, "children": { "run_training.setup": { "total": 0.04594756400001643, "count": 1, "self": 0.04594756400001643 }, "TrainerController.start_learning": { "total": 456.348804663, "count": 1, "self": 0.5279275799861125, "children": { "TrainerController._reset_env": { "total": 4.146774146999974, "count": 1, "self": 4.146774146999974 }, "TrainerController.advance": { "total": 451.53501129901383, "count": 18203, "self": 0.25898623101591056, "children": { "env_step": { "total": 451.2760250679979, "count": 18203, "self": 315.6313316119864, "children": { "SubprocessEnvManager._take_step": { "total": 135.36679393500458, "count": 18203, "self": 1.6598198360143215, "children": { "TorchPolicy.evaluate": { "total": 133.70697409899026, "count": 18203, "self": 133.70697409899026 } } }, "workers": { "total": 0.2778995210069297, "count": 18203, "self": 0.0, "children": { "worker_root": { "total": 454.7810706640008, "count": 18203, "is_parallel": true, "self": 205.05684936800037, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005320598000025711, "count": 1, "is_parallel": true, "self": 0.0039036800000076255, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014169180000180859, "count": 10, "is_parallel": true, "self": 0.0014169180000180859 } } }, "UnityEnvironment.step": { "total": 0.05406752999999753, "count": 1, "is_parallel": true, "self": 0.0006709670000191181, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003391510000483322, "count": 1, "is_parallel": true, "self": 0.0003391510000483322 }, "communicator.exchange": { "total": 0.04589412399991488, "count": 1, "is_parallel": true, "self": 0.04589412399991488 }, "steps_from_proto": { "total": 0.0071632880000152, "count": 1, "is_parallel": true, "self": 0.0054124290001027475, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017508589999124524, "count": 10, "is_parallel": true, "self": 0.0017508589999124524 } } } } } } }, "UnityEnvironment.step": { "total": 249.72422129600045, "count": 18202, "is_parallel": true, "self": 10.507203145997664, "children": { "UnityEnvironment._generate_step_input": { "total": 5.268426289009312, "count": 18202, "is_parallel": true, "self": 5.268426289009312 }, "communicator.exchange": { "total": 197.8083735270003, "count": 18202, "is_parallel": true, "self": 197.8083735270003 }, "steps_from_proto": { "total": 36.140218333993175, "count": 18202, "is_parallel": true, "self": 6.524801563997357, "children": { "_process_rank_one_or_two_observation": { "total": 29.615416769995818, "count": 182020, "is_parallel": true, "self": 29.615416769995818 } } } } } } } } } } } } }, "trainer_threads": { "total": 4.783400004271243e-05, "count": 1, "self": 4.783400004271243e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 446.4843295829396, "count": 570943, "is_parallel": true, "self": 13.148950184980094, "children": { "process_trajectory": { "total": 314.0264493609591, "count": 570943, "is_parallel": true, "self": 312.17052831395915, "children": { "RLTrainer._checkpoint": { "total": 1.8559210469999243, "count": 4, "is_parallel": true, "self": 1.8559210469999243 } } }, "_update_policy": { "total": 119.30893003700044, "count": 38, "is_parallel": true, "self": 73.02891876900264, "children": { "TorchPPOOptimizer.update": { "total": 46.28001126799779, "count": 1062, "is_parallel": true, "self": 46.28001126799779 } } } } } } } } }, "TrainerController._save_models": { "total": 0.1390438030000496, "count": 1, "self": 0.0009096829999180045, "children": { "RLTrainer._checkpoint": { "total": 0.1381341200001316, "count": 1, "self": 0.1381341200001316 } } } } } } }