{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.1773548126220703, "min": 1.1773548126220703, "max": 2.8159801959991455, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 11189.580078125, "min": 11189.580078125, "max": 28745.525390625, "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": 11.543111801147461, "min": 0.42348650097846985, "max": 11.543111801147461, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2250.90673828125, "min": 82.15637969970703, "max": 2327.415771484375, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06371357174893823, "min": 0.06371357174893823, "max": 0.07369157245585822, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2548542869957529, "min": 0.2548542869957529, "max": 0.3643832473899238, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.23352228404552328, "min": 0.1605186915668823, "max": 0.2870693533297848, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.9340891361820931, "min": 0.6420747662675292, "max": 1.3968502192520629, "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.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": 23.204545454545453, "min": 4.2272727272727275, "max": 23.204545454545453, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1021.0, "min": 186.0, "max": 1240.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 23.204545454545453, "min": 4.2272727272727275, "max": 23.204545454545453, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1021.0, "min": 186.0, "max": 1240.0, "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": "1780270039", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn /content/ml-agents/config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1780270534" }, "total": 495.14349992200005, "count": 1, "self": 0.4420597240000461, "children": { "run_training.setup": { "total": 0.02778803399996832, "count": 1, "self": 0.02778803399996832 }, "TrainerController.start_learning": { "total": 494.67365216400003, "count": 1, "self": 0.4363550629918791, "children": { "TrainerController._reset_env": { "total": 2.8667329529998824, "count": 1, "self": 2.8667329529998824 }, "TrainerController.advance": { "total": 491.2845224530083, "count": 18192, "self": 0.4676958280329018, "children": { "env_step": { "total": 361.11614637298044, "count": 18192, "self": 282.39157482395467, "children": { "SubprocessEnvManager._take_step": { "total": 78.46450938502221, "count": 18192, "self": 1.4117338420378474, "children": { "TorchPolicy.evaluate": { "total": 77.05277554298436, "count": 18192, "self": 77.05277554298436 } } }, "workers": { "total": 0.260062164003557, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 492.74949637203053, "count": 18192, "is_parallel": true, "self": 245.34001869796975, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004248583000389772, "count": 1, "is_parallel": true, "self": 0.0029222410007605504, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013263419996292214, "count": 10, "is_parallel": true, "self": 0.0013263419996292214 } } }, "UnityEnvironment.step": { "total": 0.042655761999867536, "count": 1, "is_parallel": true, "self": 0.000694779999776074, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004367030001048988, "count": 1, "is_parallel": true, "self": 0.0004367030001048988 }, "communicator.exchange": { "total": 0.03954627700022684, "count": 1, "is_parallel": true, "self": 0.03954627700022684 }, "steps_from_proto": { "total": 0.0019780019997597265, "count": 1, "is_parallel": true, "self": 0.00037597000073219533, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016020319990275311, "count": 10, "is_parallel": true, "self": 0.0016020319990275311 } } } } } } }, "UnityEnvironment.step": { "total": 247.40947767406078, "count": 18191, "is_parallel": true, "self": 11.215636189075667, "children": { "UnityEnvironment._generate_step_input": { "total": 6.0142172420191855, "count": 18191, "is_parallel": true, "self": 6.0142172420191855 }, "communicator.exchange": { "total": 189.23405829393278, "count": 18191, "is_parallel": true, "self": 189.23405829393278 }, "steps_from_proto": { "total": 40.94556594903315, "count": 18191, "is_parallel": true, "self": 7.261854872090225, "children": { "_process_rank_one_or_two_observation": { "total": 33.68371107694293, "count": 181910, "is_parallel": true, "self": 33.68371107694293 } } } } } } } } } } }, "trainer_advance": { "total": 129.70068025199498, "count": 18192, "self": 0.5409673339859182, "children": { "process_trajectory": { "total": 29.14283580800793, "count": 18192, "self": 28.684968731007302, "children": { "RLTrainer._checkpoint": { "total": 0.45786707700062834, "count": 4, "self": 0.45786707700062834 } } }, "_update_policy": { "total": 100.01687711000113, "count": 90, "self": 40.802163131007546, "children": { "TorchPPOOptimizer.update": { "total": 59.214713978993586, "count": 4587, "self": 59.214713978993586 } } } } } } }, "trainer_threads": { "total": 1.0150001799047459e-06, "count": 1, "self": 1.0150001799047459e-06 }, "TrainerController._save_models": { "total": 0.08604067999976905, "count": 1, "self": 0.000874904999818682, "children": { "RLTrainer._checkpoint": { "total": 0.08516577499995037, "count": 1, "self": 0.08516577499995037 } } } } } } }