{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9490188956260681, "min": 0.9490188956260681, "max": 2.8710436820983887, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9061.232421875, "min": 9061.232421875, "max": 29402.359375, "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": 13.172898292541504, "min": 0.28534239530563354, "max": 13.24039077758789, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2568.715087890625, "min": 55.35642623901367, "max": 2714.280029296875, "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": 0.06478935527275989, "min": 0.06350984488540859, "max": 0.07621654135585357, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.25915742109103956, "min": 0.25915742109103956, "max": 0.3810827067792678, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.18091574300299673, "min": 0.12726331237525518, "max": 0.29309817147897743, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7236629720119869, "min": 0.5090532495010207, "max": 1.4434602732824928, "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": 25.727272727272727, "min": 3.0454545454545454, "max": 25.931818181818183, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1132.0, "min": 134.0, "max": 1421.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.727272727272727, "min": 3.0454545454545454, "max": 25.931818181818183, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1132.0, "min": 134.0, "max": 1421.0, "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": "1699646594", "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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.0+cu118", "numpy_version": "1.23.5", "end_time_seconds": "1699647098" }, "total": 503.45557318800013, "count": 1, "self": 0.4341068050001695, "children": { "run_training.setup": { "total": 0.050474152999981925, "count": 1, "self": 0.050474152999981925 }, "TrainerController.start_learning": { "total": 502.97099223, "count": 1, "self": 0.5746767949982541, "children": { "TrainerController._reset_env": { "total": 8.618210733999945, "count": 1, "self": 8.618210733999945 }, "TrainerController.advance": { "total": 493.6934927320018, "count": 18200, "self": 0.29256714399343764, "children": { "env_step": { "total": 493.40092558800836, "count": 18200, "self": 343.5393476950136, "children": { "SubprocessEnvManager._take_step": { "total": 149.57605164399263, "count": 18200, "self": 1.498846626996169, "children": { "TorchPolicy.evaluate": { "total": 148.07720501699646, "count": 18200, "self": 148.07720501699646 } } }, "workers": { "total": 0.28552624900214596, "count": 18200, "self": 0.0, "children": { "worker_root": { "total": 501.59457662099635, "count": 18200, "is_parallel": true, "self": 248.49530295199452, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0065858800001024065, "count": 1, "is_parallel": true, "self": 0.004189426999914758, "children": { "_process_rank_one_or_two_observation": { "total": 0.0023964530001876483, "count": 10, "is_parallel": true, "self": 0.0023964530001876483 } } }, "UnityEnvironment.step": { "total": 0.03241527800003041, "count": 1, "is_parallel": true, "self": 0.0003689610000492394, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00024516300004506775, "count": 1, "is_parallel": true, "self": 0.00024516300004506775 }, "communicator.exchange": { "total": 0.030015176999995674, "count": 1, "is_parallel": true, "self": 0.030015176999995674 }, "steps_from_proto": { "total": 0.0017859769999404307, "count": 1, "is_parallel": true, "self": 0.000348924000036277, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014370529999041537, "count": 10, "is_parallel": true, "self": 0.0014370529999041537 } } } } } } }, "UnityEnvironment.step": { "total": 253.09927366900183, "count": 18199, "is_parallel": true, "self": 10.959544689016639, "children": { "UnityEnvironment._generate_step_input": { "total": 5.447271651994811, "count": 18199, "is_parallel": true, "self": 5.447271651994811 }, "communicator.exchange": { "total": 201.68985558098984, "count": 18199, "is_parallel": true, "self": 201.68985558098984 }, "steps_from_proto": { "total": 35.00260174700054, "count": 18199, "is_parallel": true, "self": 6.549726212958035, "children": { "_process_rank_one_or_two_observation": { "total": 28.452875534042505, "count": 181990, "is_parallel": true, "self": 28.452875534042505 } } } } } } } } } } } } }, "trainer_threads": { "total": 3.661200003080012e-05, "count": 1, "self": 3.661200003080012e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 489.5708137720235, "count": 513555, "is_parallel": true, "self": 10.865640205033515, "children": { "process_trajectory": { "total": 276.02485261299, "count": 513555, "is_parallel": true, "self": 275.27794842799017, "children": { "RLTrainer._checkpoint": { "total": 0.7469041849998348, "count": 4, "is_parallel": true, "self": 0.7469041849998348 } } }, "_update_policy": { "total": 202.68032095399997, "count": 90, "is_parallel": true, "self": 74.66826478800226, "children": { "TorchPPOOptimizer.update": { "total": 128.0120561659977, "count": 4584, "is_parallel": true, "self": 128.0120561659977 } } } } } } } } }, "TrainerController._save_models": { "total": 0.08457535699994878, "count": 1, "self": 0.000883002999898963, "children": { "RLTrainer._checkpoint": { "total": 0.08369235400004982, "count": 1, "self": 0.08369235400004982 } } } } } } }