{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8054616451263428, "min": 0.7970304489135742, "max": 2.796876907348633, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7655.107421875, "min": 7655.107421875, "max": 28550.51953125, "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": 13.283506393432617, "min": 0.5775161981582642, "max": 13.283506393432617, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2590.28369140625, "min": 112.03813934326172, "max": 2703.60400390625, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06817431198832985, "min": 0.06756688092392778, "max": 0.07106685170886042, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2726972479533194, "min": 0.2707678186177525, "max": 0.3552740258691832, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.16712515845429154, "min": 0.13125464004823537, "max": 0.28420236393809317, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.6685006338171662, "min": 0.5250185601929415, "max": 1.421011819690466, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 2.694097306000002e-06, "min": 2.694097306000002e-06, "max": 9.7294002706e-05, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 1.0776389224000008e-05, "min": 1.0776389224000008e-05, "max": 0.00046172003828000015, "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": 0.9617200000000001, "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.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.Environment.CumulativeReward.mean": { "value": 26.113636363636363, "min": 4.590909090909091, "max": 26.113636363636363, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1149.0, "min": 202.0, "max": 1429.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 26.113636363636363, "min": 4.590909090909091, "max": 26.113636363636363, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1149.0, "min": 202.0, "max": 1429.0, "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": "1741888791", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget2 --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1741891744" }, "total": 2952.4862104669996, "count": 1, "self": 0.7480669719993784, "children": { "run_training.setup": { "total": 0.021806628000376804, "count": 1, "self": 0.021806628000376804 }, "TrainerController.start_learning": { "total": 2951.716336867, "count": 1, "self": 0.4181947549677716, "children": { "TrainerController._reset_env": { "total": 1.9771829509995769, "count": 1, "self": 1.9771829509995769 }, "TrainerController.advance": { "total": 2949.177502338032, "count": 18192, "self": 0.42027468496689835, "children": { "env_step": { "total": 318.98213006004517, "count": 18192, "self": 243.04176356817106, "children": { "SubprocessEnvManager._take_step": { "total": 75.69720600698656, "count": 18192, "self": 1.3682364289729776, "children": { "TorchPolicy.evaluate": { "total": 74.32896957801358, "count": 18192, "self": 74.32896957801358 } } }, "workers": { "total": 0.2431604848875395, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 2950.04085903698, "count": 18192, "is_parallel": true, "self": 2737.4613575169233, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.003148694999708823, "count": 1, "is_parallel": true, "self": 0.0009813129986468994, "children": { "_process_rank_one_or_two_observation": { "total": 0.002167382001061924, "count": 10, "is_parallel": true, "self": 0.002167382001061924 } } }, "UnityEnvironment.step": { "total": 0.06359044999999242, "count": 1, "is_parallel": true, "self": 0.0005663920001097722, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004438809996827331, "count": 1, "is_parallel": true, "self": 0.0004438809996827331 }, "communicator.exchange": { "total": 0.06072710500029643, "count": 1, "is_parallel": true, "self": 0.06072710500029643 }, "steps_from_proto": { "total": 0.0018530719999034773, "count": 1, "is_parallel": true, "self": 0.00037505399996007327, "children": { "_process_rank_one_or_two_observation": { "total": 0.001478017999943404, "count": 10, "is_parallel": true, "self": 0.001478017999943404 } } } } } } }, "UnityEnvironment.step": { "total": 212.5795015200565, "count": 18191, "is_parallel": true, "self": 9.79515217006292, "children": { "UnityEnvironment._generate_step_input": { "total": 5.54457634304481, "count": 18191, "is_parallel": true, "self": 5.54457634304481 }, "communicator.exchange": { "total": 164.40729102195473, "count": 18191, "is_parallel": true, "self": 164.40729102195473 }, "steps_from_proto": { "total": 32.83248198499405, "count": 18191, "is_parallel": true, "self": 6.024030621067595, "children": { "_process_rank_one_or_two_observation": { "total": 26.80845136392645, "count": 181910, "is_parallel": true, "self": 26.80845136392645 } } } } } } } } } } }, "trainer_advance": { "total": 2629.77509759302, "count": 18192, "self": 0.4979380089944243, "children": { "process_trajectory": { "total": 28.03423390302396, "count": 18192, "self": 27.570013334023315, "children": { "RLTrainer._checkpoint": { "total": 0.4642205690006449, "count": 4, "self": 0.4642205690006449 } } }, "_update_policy": { "total": 2601.2429256810015, "count": 90, "self": 1052.9212974659663, "children": { "TorchPPOOptimizer.update": { "total": 1548.3216282150352, "count": 122320, "self": 1548.3216282150352 } } } } } } }, "trainer_threads": { "total": 1.2950004020240158e-06, "count": 1, "self": 1.2950004020240158e-06 }, "TrainerController._save_models": { "total": 0.14345552800023142, "count": 1, "self": 0.001372257000184618, "children": { "RLTrainer._checkpoint": { "total": 0.1420832710000468, "count": 1, "self": 0.1420832710000468 } } } } } } }