{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9699707627296448, "min": 0.9699707627296448, "max": 2.865546464920044, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9282.6201171875, "min": 9282.6201171875, "max": 29346.0625, "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": 12.84813404083252, "min": 0.11813946068286896, "max": 12.848520278930664, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2505.38623046875, "min": 22.919055938720703, "max": 2621.09814453125, "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": 0.06894986994017267, "min": 0.06309332864281411, "max": 0.073573074280855, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2757994797606907, "min": 0.2567894669041647, "max": 0.367865371404275, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20688518648054086, "min": 0.12235718562413811, "max": 0.2742537845875702, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8275407459221634, "min": 0.48942874249655244, "max": 1.3407601308004529, "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": 25.0, "min": 3.727272727272727, "max": 25.5, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1100.0, "min": 164.0, "max": 1392.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.0, "min": 3.727272727272727, "max": 25.5, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1100.0, "min": 164.0, "max": 1392.0, "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": "1679733600", "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": "1679734101" }, "total": 500.678941917, "count": 1, "self": 0.43890626799998245, "children": { "run_training.setup": { "total": 0.1098534100000279, "count": 1, "self": 0.1098534100000279 }, "TrainerController.start_learning": { "total": 500.13018223899996, "count": 1, "self": 0.5913378370026976, "children": { "TrainerController._reset_env": { "total": 9.668060224999977, "count": 1, "self": 9.668060224999977 }, "TrainerController.advance": { "total": 489.71332428499727, "count": 18202, "self": 0.29585842999631495, "children": { "env_step": { "total": 489.41746585500096, "count": 18202, "self": 353.3981354000054, "children": { "SubprocessEnvManager._take_step": { "total": 135.73181314199132, "count": 18202, "self": 2.342312920001177, "children": { "TorchPolicy.evaluate": { "total": 133.38950022199015, "count": 18202, "self": 133.38950022199015 } } }, "workers": { "total": 0.2875173130042299, "count": 18202, "self": 0.0, "children": { "worker_root": { "total": 498.5599753679962, "count": 18202, "is_parallel": true, "self": 240.0011533499969, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005576976999975614, "count": 1, "is_parallel": true, "self": 0.0037245319997509796, "children": { "_process_rank_one_or_two_observation": { "total": 0.001852445000224634, "count": 10, "is_parallel": true, "self": 0.001852445000224634 } } }, "UnityEnvironment.step": { "total": 0.11362632099996972, "count": 1, "is_parallel": true, "self": 0.0006712519999041433, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004331630000251607, "count": 1, "is_parallel": true, "self": 0.0004331630000251607 }, "communicator.exchange": { "total": 0.1094908420000138, "count": 1, "is_parallel": true, "self": 0.1094908420000138 }, "steps_from_proto": { "total": 0.0030310640000266176, "count": 1, "is_parallel": true, "self": 0.001370866000058868, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016601979999677496, "count": 10, "is_parallel": true, "self": 0.0016601979999677496 } } } } } } }, "UnityEnvironment.step": { "total": 258.55882201799926, "count": 18201, "is_parallel": true, "self": 10.061698723989537, "children": { "UnityEnvironment._generate_step_input": { "total": 5.666690318002509, "count": 18201, "is_parallel": true, "self": 5.666690318002509 }, "communicator.exchange": { "total": 208.07410094900285, "count": 18201, "is_parallel": true, "self": 208.07410094900285 }, "steps_from_proto": { "total": 34.75633202700436, "count": 18201, "is_parallel": true, "self": 7.072017229994799, "children": { "_process_rank_one_or_two_observation": { "total": 27.684314797009563, "count": 182010, "is_parallel": true, "self": 27.684314797009563 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0001573050000160947, "count": 1, "self": 0.0001573050000160947, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 485.85068166195873, "count": 444154, "is_parallel": true, "self": 11.427635837958235, "children": { "process_trajectory": { "total": 272.3984482090012, "count": 444154, "is_parallel": true, "self": 270.8453012340011, "children": { "RLTrainer._checkpoint": { "total": 1.553146975000061, "count": 4, "is_parallel": true, "self": 1.553146975000061 } } }, "_update_policy": { "total": 202.02459761499932, "count": 90, "is_parallel": true, "self": 75.97907427200289, "children": { "TorchPPOOptimizer.update": { "total": 126.04552334299643, "count": 4584, "is_parallel": true, "self": 126.04552334299643 } } } } } } } } }, "TrainerController._save_models": { "total": 0.15730258700000377, "count": 1, "self": 0.0008454439999923125, "children": { "RLTrainer._checkpoint": { "total": 0.15645714300001146, "count": 1, "self": 0.15645714300001146 } } } } } } }