{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.995881199836731, "min": 0.995881199836731, "max": 2.8476357460021973, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9508.673828125, "min": 9508.673828125, "max": 29193.9609375, "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": 12.668417930603027, "min": 0.35509130358695984, "max": 12.668417930603027, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2470.341552734375, "min": 68.88771057128906, "max": 2556.125244140625, "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": 0.07736197417219884, "min": 0.06277145443454281, "max": 0.07736197417219884, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.30944789668879535, "min": 0.25108581773817124, "max": 0.3752618936003487, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19227506833917957, "min": 0.12349911324232452, "max": 0.273880443444439, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7691002733567183, "min": 0.49399645296929806, "max": 1.3694022172221951, "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": 25.136363636363637, "min": 3.75, "max": 25.21818181818182, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1106.0, "min": 165.0, "max": 1387.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.136363636363637, "min": 3.75, "max": 25.21818181818182, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1106.0, "min": 165.0, "max": 1387.0, "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": "1695050476", "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": "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": "1695050997" }, "total": 521.4746987660001, "count": 1, "self": 0.43622435000008863, "children": { "run_training.setup": { "total": 0.05006093800000144, "count": 1, "self": 0.05006093800000144 }, "TrainerController.start_learning": { "total": 520.988413478, "count": 1, "self": 0.7027507870028558, "children": { "TrainerController._reset_env": { "total": 5.406536584000037, "count": 1, "self": 5.406536584000037 }, "TrainerController.advance": { "total": 514.7241401629972, "count": 18202, "self": 0.34292897099248876, "children": { "env_step": { "total": 514.3812111920047, "count": 18202, "self": 374.90876719600305, "children": { "SubprocessEnvManager._take_step": { "total": 139.1386156940104, "count": 18202, "self": 2.0237801020139727, "children": { "TorchPolicy.evaluate": { "total": 137.11483559199644, "count": 18202, "self": 137.11483559199644 } } }, "workers": { "total": 0.33382830199121827, "count": 18202, "self": 0.0, "children": { "worker_root": { "total": 519.1901535949905, "count": 18202, "is_parallel": true, "self": 240.3788316169941, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006435721000002559, "count": 1, "is_parallel": true, "self": 0.0048303460000056475, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016053749999969114, "count": 10, "is_parallel": true, "self": 0.0016053749999969114 } } }, "UnityEnvironment.step": { "total": 0.06384594600001492, "count": 1, "is_parallel": true, "self": 0.0007196770000064134, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003756250000037653, "count": 1, "is_parallel": true, "self": 0.0003756250000037653 }, "communicator.exchange": { "total": 0.05859163500002751, "count": 1, "is_parallel": true, "self": 0.05859163500002751 }, "steps_from_proto": { "total": 0.004159008999977232, "count": 1, "is_parallel": true, "self": 0.0006701220000309149, "children": { "_process_rank_one_or_two_observation": { "total": 0.003488886999946317, "count": 10, "is_parallel": true, "self": 0.003488886999946317 } } } } } } }, "UnityEnvironment.step": { "total": 278.81132197799644, "count": 18201, "is_parallel": true, "self": 11.467148742004952, "children": { "UnityEnvironment._generate_step_input": { "total": 5.970345002991223, "count": 18201, "is_parallel": true, "self": 5.970345002991223 }, "communicator.exchange": { "total": 220.93250015500257, "count": 18201, "is_parallel": true, "self": 220.93250015500257 }, "steps_from_proto": { "total": 40.441328077997696, "count": 18201, "is_parallel": true, "self": 7.7517876940111705, "children": { "_process_rank_one_or_two_observation": { "total": 32.689540383986525, "count": 182010, "is_parallel": true, "self": 32.689540383986525 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00014133799993487628, "count": 1, "self": 0.00014133799993487628, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 510.8398350819798, "count": 470823, "is_parallel": true, "self": 10.919820203938912, "children": { "process_trajectory": { "total": 283.71770846204146, "count": 470823, "is_parallel": true, "self": 282.4442122290414, "children": { "RLTrainer._checkpoint": { "total": 1.2734962330000599, "count": 4, "is_parallel": true, "self": 1.2734962330000599 } } }, "_update_policy": { "total": 216.20230641599943, "count": 90, "is_parallel": true, "self": 80.33856901800021, "children": { "TorchPPOOptimizer.update": { "total": 135.86373739799922, "count": 4584, "is_parallel": true, "self": 135.86373739799922 } } } } } } } } }, "TrainerController._save_models": { "total": 0.1548446059999833, "count": 1, "self": 0.0008717010000509617, "children": { "RLTrainer._checkpoint": { "total": 0.15397290499993233, "count": 1, "self": 0.15397290499993233 } } } } } } }