{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8054758906364441, "min": 0.8009305596351624, "max": 2.8582563400268555, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7690.68408203125, "min": 7690.68408203125, "max": 29271.40234375, "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": 12.0610990524292, "min": 0.339819997549057, "max": 12.0610990524292, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2351.914306640625, "min": 65.92507934570312, "max": 2435.798828125, "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": 0.06418307264692547, "min": 0.05834482358919808, "max": 0.08134209155147855, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.25673229058770186, "min": 0.23337929435679233, "max": 0.37258580058565427, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.17640990373112406, "min": 0.12407946701083954, "max": 0.26866966135361614, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7056396149244962, "min": 0.49631786804335815, "max": 1.3433483067680807, "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": 23.84090909090909, "min": 3.4545454545454546, "max": 23.84090909090909, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1049.0, "min": 152.0, "max": 1300.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 23.84090909090909, "min": 3.4545454545454546, "max": 23.84090909090909, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1049.0, "min": 152.0, "max": 1300.0, "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": "1674209740", "python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \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": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.21.6", "end_time_seconds": "1674210146" }, "total": 406.00482873500005, "count": 1, "self": 0.39378250599997955, "children": { "run_training.setup": { "total": 0.10185389900004793, "count": 1, "self": 0.10185389900004793 }, "TrainerController.start_learning": { "total": 405.50919233, "count": 1, "self": 0.4858894219960348, "children": { "TrainerController._reset_env": { "total": 9.693903237999962, "count": 1, "self": 9.693903237999962 }, "TrainerController.advance": { "total": 395.2170873940041, "count": 18202, "self": 0.24122978999878342, "children": { "env_step": { "total": 394.97585760400534, "count": 18202, "self": 256.6813828049893, "children": { "SubprocessEnvManager._take_step": { "total": 138.0527107820085, "count": 18202, "self": 1.530502855994314, "children": { "TorchPolicy.evaluate": { "total": 136.52220792601418, "count": 18202, "self": 29.632950983015235, "children": { "TorchPolicy.sample_actions": { "total": 106.88925694299894, "count": 18202, "self": 106.88925694299894 } } } } }, "workers": { "total": 0.24176401700754013, "count": 18202, "self": 0.0, "children": { "worker_root": { "total": 404.3770503500017, "count": 18202, "is_parallel": true, "self": 195.90730608701085, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006042803000013919, "count": 1, "is_parallel": true, "self": 0.003461227000002509, "children": { "_process_rank_one_or_two_observation": { "total": 0.0025815760000114096, "count": 10, "is_parallel": true, "self": 0.0025815760000114096 } } }, "UnityEnvironment.step": { "total": 0.03465083499997945, "count": 1, "is_parallel": true, "self": 0.0006417909999072435, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002960320000511274, "count": 1, "is_parallel": true, "self": 0.0002960320000511274 }, "communicator.exchange": { "total": 0.028799805999938144, "count": 1, "is_parallel": true, "self": 0.028799805999938144 }, "steps_from_proto": { "total": 0.004913206000082937, "count": 1, "is_parallel": true, "self": 0.003512607000175194, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014005989999077428, "count": 10, "is_parallel": true, "self": 0.0014005989999077428 } } } } } } }, "UnityEnvironment.step": { "total": 208.46974426299084, "count": 18201, "is_parallel": true, "self": 7.844125820000841, "children": { "UnityEnvironment._generate_step_input": { "total": 4.671283004992574, "count": 18201, "is_parallel": true, "self": 4.671283004992574 }, "communicator.exchange": { "total": 167.81610675099807, "count": 18201, "is_parallel": true, "self": 167.81610675099807 }, "steps_from_proto": { "total": 28.138228686999355, "count": 18201, "is_parallel": true, "self": 5.9932762160087805, "children": { "_process_rank_one_or_two_observation": { "total": 22.144952470990575, "count": 182010, "is_parallel": true, "self": 22.144952470990575 } } } } } } } } } } } } }, "trainer_threads": { "total": 3.540199998042226e-05, "count": 1, "self": 3.540199998042226e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 392.5171442399783, "count": 330407, "is_parallel": true, "self": 8.532465856990825, "children": { "process_trajectory": { "total": 225.63378982898735, "count": 330407, "is_parallel": true, "self": 224.91044597898724, "children": { "RLTrainer._checkpoint": { "total": 0.7233438500001057, "count": 4, "is_parallel": true, "self": 0.7233438500001057 } } }, "_update_policy": { "total": 158.3508885540001, "count": 90, "is_parallel": true, "self": 39.99174963999917, "children": { "TorchPPOOptimizer.update": { "total": 118.35913891400094, "count": 4587, "is_parallel": true, "self": 118.35913891400094 } } } } } } } } }, "TrainerController._save_models": { "total": 0.11227687399991737, "count": 1, "self": 0.0007991859998810469, "children": { "RLTrainer._checkpoint": { "total": 0.11147768800003632, "count": 1, "self": 0.11147768800003632 } } } } } } }