{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.3880797624588013, "min": 1.3880797624588013, "max": 2.8517308235168457, "count": 13 }, "SnowballTarget.Policy.Entropy.sum": { "value": 14306.9375, "min": 13513.2646484375, "max": 29204.57421875, "count": 13 }, "SnowballTarget.Step.mean": { "value": 129992.0, "min": 9952.0, "max": 129992.0, "count": 13 }, "SnowballTarget.Step.sum": { "value": 129992.0, "min": 9952.0, "max": 129992.0, "count": 13 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 10.128174781799316, "min": 0.2832825779914856, "max": 10.128174781799316, "count": 13 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2076.27587890625, "min": 54.956817626953125, "max": 2076.27587890625, "count": 13 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 13 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 13 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06962355011389318, "min": 0.06357419257832339, "max": 0.07463602524347188, "count": 13 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.34811775056946587, "min": 0.2603094176510258, "max": 0.3731801262173594, "count": 13 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.22773249371379028, "min": 0.11697891320321052, "max": 0.2781759425705554, "count": 13 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 1.1386624685689515, "min": 0.4679156528128421, "max": 1.390879712852777, "count": 13 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 0.00011203206265599998, "min": 0.00011203206265599998, "max": 0.000291882002706, "count": 13 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 0.0005601603132799999, "min": 0.000507528230824, "max": 0.00138516003828, "count": 13 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.13734400000000002, "min": 0.13734400000000002, "max": 0.19729400000000002, "count": 13 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.6867200000000001, "min": 0.569176, "max": 0.96172, "count": 13 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0018734656000000006, "min": 0.0018734656000000006, "max": 0.0048649706, "count": 13 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.009367328000000003, "min": 0.008481882400000001, "max": 0.023089828, "count": 13 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 21.509090909090908, "min": 3.4318181818181817, "max": 21.509090909090908, "count": 13 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1183.0, "min": 151.0, "max": 1183.0, "count": 13 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 21.509090909090908, "min": 3.4318181818181817, "max": 21.509090909090908, "count": 13 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1183.0, "min": 151.0, "max": 1183.0, "count": 13 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 13 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 13 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1713175591", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1713175922" }, "total": 331.8479391139999, "count": 1, "self": 0.014853138999910698, "children": { "run_training.setup": { "total": 0.06150647200001913, "count": 1, "self": 0.06150647200001913 }, "TrainerController.start_learning": { "total": 331.771579503, "count": 1, "self": 1.3985338750021583, "children": { "TrainerController._reset_env": { "total": 3.6751574590000473, "count": 1, "self": 3.6751574590000473 }, "TrainerController.advance": { "total": 326.5891922509978, "count": 12198, "self": 0.21753435899802298, "children": { "env_step": { "total": 326.3716578919998, "count": 12198, "self": 212.15058538000767, "children": { "SubprocessEnvManager._take_step": { "total": 113.99187090299517, "count": 12198, "self": 1.1206303279833492, "children": { "TorchPolicy.evaluate": { "total": 112.87124057501183, "count": 12198, "self": 112.87124057501183 } } }, "workers": { "total": 0.2292016089969593, "count": 12197, "self": 0.0, "children": { "worker_root": { "total": 329.7804401870036, "count": 12197, "is_parallel": true, "self": 162.73411530801604, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005380938000030255, "count": 1, "is_parallel": true, "self": 0.0036088850000624006, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017720529999678547, "count": 10, "is_parallel": true, "self": 0.0017720529999678547 } } }, "UnityEnvironment.step": { "total": 0.04277813399994557, "count": 1, "is_parallel": true, "self": 0.0007616190000589995, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004443739999260288, "count": 1, "is_parallel": true, "self": 0.0004443739999260288 }, "communicator.exchange": { "total": 0.03936325899996973, "count": 1, "is_parallel": true, "self": 0.03936325899996973 }, "steps_from_proto": { "total": 0.0022088819999908083, "count": 1, "is_parallel": true, "self": 0.000457378000078279, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017515039999125293, "count": 10, "is_parallel": true, "self": 0.0017515039999125293 } } } } } } }, "UnityEnvironment.step": { "total": 167.04632487898755, "count": 12196, "is_parallel": true, "self": 7.698381415986773, "children": { "UnityEnvironment._generate_step_input": { "total": 4.00134046099754, "count": 12196, "is_parallel": true, "self": 4.00134046099754 }, "communicator.exchange": { "total": 130.64722692800422, "count": 12196, "is_parallel": true, "self": 130.64722692800422 }, "steps_from_proto": { "total": 24.69937607399902, "count": 12196, "is_parallel": true, "self": 4.812352262992249, "children": { "_process_rank_one_or_two_observation": { "total": 19.88702381100677, "count": 121960, "is_parallel": true, "self": 19.88702381100677 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.001165099999980157, "count": 1, "self": 0.001165099999980157, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 323.2787261299071, "count": 508865, "is_parallel": true, "self": 11.001617000848796, "children": { "process_trajectory": { "total": 180.47398547505838, "count": 508865, "is_parallel": true, "self": 180.12943518305838, "children": { "RLTrainer._checkpoint": { "total": 0.3445502920000081, "count": 2, "is_parallel": true, "self": 0.3445502920000081 } } }, "_update_policy": { "total": 131.80312365399993, "count": 61, "is_parallel": true, "self": 38.18519688700246, "children": { "TorchPPOOptimizer.update": { "total": 93.61792676699747, "count": 3108, "is_parallel": true, "self": 93.61792676699747 } } } } } } } } }, "TrainerController._save_models": { "total": 0.10753081799998654, "count": 1, "self": 0.0016270780001832463, "children": { "RLTrainer._checkpoint": { "total": 0.10590373999980329, "count": 1, "self": 0.10590373999980329 } } } } } } }