{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.869920551776886, "min": 0.869920551776886, "max": 2.8605337142944336, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8334.708984375, "min": 8334.708984375, "max": 29357.658203125, "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": 12.986538887023926, "min": 0.4548584520816803, "max": 12.986538887023926, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2532.375, "min": 88.24253845214844, "max": 2639.278564453125, "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": 0.06958413641633324, "min": 0.06114401938005662, "max": 0.07450872718792537, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.27833654566533295, "min": 0.24457607752022648, "max": 0.3725436359396268, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20067991929895737, "min": 0.13251137769525395, "max": 0.28550941840398547, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8027196771958295, "min": 0.5300455107810158, "max": 1.4263725561254164, "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": 25.272727272727273, "min": 3.8181818181818183, "max": 25.90909090909091, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1112.0, "min": 168.0, "max": 1380.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.272727272727273, "min": 3.8181818181818183, "max": 25.90909090909091, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1112.0, "min": 168.0, "max": 1380.0, "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": "1679854178", "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 --resume", "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": "1679854624" }, "total": 445.30463968200024, "count": 1, "self": 0.7003931940000712, "children": { "run_training.setup": { "total": 0.16631923699992512, "count": 1, "self": 0.16631923699992512 }, "TrainerController.start_learning": { "total": 444.43792725100025, "count": 1, "self": 0.510671556983425, "children": { "TrainerController._reset_env": { "total": 6.598161553999944, "count": 1, "self": 6.598161553999944 }, "TrainerController.advance": { "total": 437.1276702440173, "count": 18221, "self": 0.2641556780290557, "children": { "env_step": { "total": 436.8635145659882, "count": 18221, "self": 315.64339778798467, "children": { "SubprocessEnvManager._take_step": { "total": 120.96878056900232, "count": 18221, "self": 2.3084072369699697, "children": { "TorchPolicy.evaluate": { "total": 118.66037333203235, "count": 18221, "self": 118.66037333203235 } } }, "workers": { "total": 0.2513362090012379, "count": 18221, "self": 0.0, "children": { "worker_root": { "total": 443.08569893996764, "count": 18221, "is_parallel": true, "self": 210.7851696609846, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0028299110001626104, "count": 1, "is_parallel": true, "self": 0.0007844020001357421, "children": { "_process_rank_one_or_two_observation": { "total": 0.0020455090000268683, "count": 10, "is_parallel": true, "self": 0.0020455090000268683 } } }, "UnityEnvironment.step": { "total": 0.04321608099985497, "count": 1, "is_parallel": true, "self": 0.0005422860001544905, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002784439998322341, "count": 1, "is_parallel": true, "self": 0.0002784439998322341 }, "communicator.exchange": { "total": 0.04035629099985272, "count": 1, "is_parallel": true, "self": 0.04035629099985272 }, "steps_from_proto": { "total": 0.0020390600000155246, "count": 1, "is_parallel": true, "self": 0.0003732719997060485, "children": { "_process_rank_one_or_two_observation": { "total": 0.001665788000309476, "count": 10, "is_parallel": true, "self": 0.001665788000309476 } } } } } } }, "UnityEnvironment.step": { "total": 232.30052927898305, "count": 18220, "is_parallel": true, "self": 9.212731274995122, "children": { "UnityEnvironment._generate_step_input": { "total": 5.038131925012522, "count": 18220, "is_parallel": true, "self": 5.038131925012522 }, "communicator.exchange": { "total": 188.57687351298068, "count": 18220, "is_parallel": true, "self": 188.57687351298068 }, "steps_from_proto": { "total": 29.472792565994723, "count": 18220, "is_parallel": true, "self": 5.734901641960278, "children": { "_process_rank_one_or_two_observation": { "total": 23.737890924034446, "count": 182200, "is_parallel": true, "self": 23.737890924034446 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00012063099984516157, "count": 1, "self": 0.00012063099984516157, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 433.987615192955, "count": 387564, "is_parallel": true, "self": 9.119460632087339, "children": { "process_trajectory": { "total": 242.9217854778658, "count": 387564, "is_parallel": true, "self": 241.41471672186572, "children": { "RLTrainer._checkpoint": { "total": 1.5070687560000806, "count": 4, "is_parallel": true, "self": 1.5070687560000806 } } }, "_update_policy": { "total": 181.94636908300185, "count": 90, "is_parallel": true, "self": 66.33845962000191, "children": { "TorchPPOOptimizer.update": { "total": 115.60790946299994, "count": 4587, "is_parallel": true, "self": 115.60790946299994 } } } } } } } } }, "TrainerController._save_models": { "total": 0.20130326499975126, "count": 1, "self": 0.00184807899995576, "children": { "RLTrainer._checkpoint": { "total": 0.1994551859997955, "count": 1, "self": 0.1994551859997955 } } } } } } }