{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.05338716506958, "min": 1.05338716506958, "max": 2.8590540885925293, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 10080.9150390625, "min": 10080.9150390625, "max": 29342.47265625, "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": 11.936591148376465, "min": 0.38258469104766846, "max": 11.936591148376465, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2327.63525390625, "min": 74.22142791748047, "max": 2402.373046875, "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": 0.06913626900224663, "min": 0.06178730253230634, "max": 0.0759000577238005, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.27654507600898653, "min": 0.2567769905130548, "max": 0.3795002886190025, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20873651423436754, "min": 0.1387146952557469, "max": 0.2734910408217533, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8349460569374701, "min": 0.5548587810229876, "max": 1.2654076312102522, "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": 23.977272727272727, "min": 3.8863636363636362, "max": 23.977272727272727, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1055.0, "min": 171.0, "max": 1311.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 23.977272727272727, "min": 3.8863636363636362, "max": 23.977272727272727, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1055.0, "min": 171.0, "max": 1311.0, "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": "1680946686", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[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": "1680947293" }, "total": 606.806786807, "count": 1, "self": 0.6396913060000315, "children": { "run_training.setup": { "total": 0.25467186200000924, "count": 1, "self": 0.25467186200000924 }, "TrainerController.start_learning": { "total": 605.9124236389999, "count": 1, "self": 0.9458133859968711, "children": { "TrainerController._reset_env": { "total": 1.305658333999986, "count": 1, "self": 1.305658333999986 }, "TrainerController.advance": { "total": 603.508910703003, "count": 18204, "self": 0.4649136019936577, "children": { "env_step": { "total": 603.0439971010094, "count": 18204, "self": 491.9772780220218, "children": { "SubprocessEnvManager._take_step": { "total": 110.6092721659852, "count": 18204, "self": 2.8578475239887666, "children": { "TorchPolicy.evaluate": { "total": 107.75142464199644, "count": 18204, "self": 107.75142464199644 } } }, "workers": { "total": 0.4574469130023999, "count": 18204, "self": 0.0, "children": { "worker_root": { "total": 603.6023964810075, "count": 18204, "is_parallel": true, "self": 254.35592098701147, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00877268199997161, "count": 1, "is_parallel": true, "self": 0.005024787000024844, "children": { "_process_rank_one_or_two_observation": { "total": 0.003747894999946766, "count": 10, "is_parallel": true, "self": 0.003747894999946766 } } }, "UnityEnvironment.step": { "total": 0.10290686299993013, "count": 1, "is_parallel": true, "self": 0.0008003099999314145, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005242810000254394, "count": 1, "is_parallel": true, "self": 0.0005242810000254394 }, "communicator.exchange": { "total": 0.09386212200001864, "count": 1, "is_parallel": true, "self": 0.09386212200001864 }, "steps_from_proto": { "total": 0.007720149999954629, "count": 1, "is_parallel": true, "self": 0.0005472180000651861, "children": { "_process_rank_one_or_two_observation": { "total": 0.0071729319998894425, "count": 10, "is_parallel": true, "self": 0.0071729319998894425 } } } } } } }, "UnityEnvironment.step": { "total": 349.24647549399606, "count": 18203, "is_parallel": true, "self": 14.522918412005197, "children": { "UnityEnvironment._generate_step_input": { "total": 8.003773373988906, "count": 18203, "is_parallel": true, "self": 8.003773373988906 }, "communicator.exchange": { "total": 280.6770249210043, "count": 18203, "is_parallel": true, "self": 280.6770249210043 }, "steps_from_proto": { "total": 46.04275878699764, "count": 18203, "is_parallel": true, "self": 9.675356543998987, "children": { "_process_rank_one_or_two_observation": { "total": 36.36740224299865, "count": 182030, "is_parallel": true, "self": 36.36740224299865 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0002598040000520996, "count": 1, "self": 0.0002598040000520996, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 597.3262048590668, "count": 712640, "is_parallel": true, "self": 17.478520270068884, "children": { "process_trajectory": { "total": 325.07554716899756, "count": 712640, "is_parallel": true, "self": 324.0385568169977, "children": { "RLTrainer._checkpoint": { "total": 1.0369903519998616, "count": 4, "is_parallel": true, "self": 1.0369903519998616 } } }, "_update_policy": { "total": 254.77213742000038, "count": 90, "is_parallel": true, "self": 89.91283004899833, "children": { "TorchPPOOptimizer.update": { "total": 164.85930737100205, "count": 4587, "is_parallel": true, "self": 164.85930737100205 } } } } } } } } }, "TrainerController._save_models": { "total": 0.15178141199999118, "count": 1, "self": 0.0018060350000723702, "children": { "RLTrainer._checkpoint": { "total": 0.1499753769999188, "count": 1, "self": 0.1499753769999188 } } } } } } }