{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9582071304321289, "min": 0.9558883309364319, "max": 2.8218321800231934, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9106.80078125, "min": 9106.80078125, "max": 28805.263671875, "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": 12.68222427368164, "min": 0.2609883248806, "max": 12.68222427368164, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2473.03369140625, "min": 50.631736755371094, "max": 2553.0322265625, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06602759550450549, "min": 0.06267087445189198, "max": 0.07843982646248632, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.26411038201802195, "min": 0.25068349780756793, "max": 0.37705844064932503, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20134252609283315, "min": 0.1173952875656587, "max": 0.2709998004868919, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8053701043713326, "min": 0.4695811502626348, "max": 1.3421193352516958, "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": 24.818181818181817, "min": 3.3181818181818183, "max": 25.204545454545453, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1092.0, "min": 146.0, "max": 1365.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.818181818181817, "min": 3.3181818181818183, "max": 25.204545454545453, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1092.0, "min": 146.0, "max": 1365.0, "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": "1747926138", "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=SnowballTarget1 --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.7.0+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1747926689" }, "total": 550.954772967, "count": 1, "self": 0.9874505670002236, "children": { "run_training.setup": { "total": 0.04123396399995727, "count": 1, "self": 0.04123396399995727 }, "TrainerController.start_learning": { "total": 549.9260884359999, "count": 1, "self": 0.6324991179820927, "children": { "TrainerController._reset_env": { "total": 4.537284991000092, "count": 1, "self": 4.537284991000092 }, "TrainerController.advance": { "total": 544.6250314920178, "count": 18192, "self": 0.6489709120073712, "children": { "env_step": { "total": 383.5529264849856, "count": 18192, "self": 328.1585090899939, "children": { "SubprocessEnvManager._take_step": { "total": 55.025207618994955, "count": 18192, "self": 1.9532846969983666, "children": { "TorchPolicy.evaluate": { "total": 53.07192292199659, "count": 18192, "self": 53.07192292199659 } } }, "workers": { "total": 0.369209775996751, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 547.7989117530034, "count": 18192, "is_parallel": true, "self": 263.5998554720088, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.008733473000006597, "count": 1, "is_parallel": true, "self": 0.005871244999866576, "children": { "_process_rank_one_or_two_observation": { "total": 0.0028622280001400213, "count": 10, "is_parallel": true, "self": 0.0028622280001400213 } } }, "UnityEnvironment.step": { "total": 0.08734739500005162, "count": 1, "is_parallel": true, "self": 0.0006839450001052683, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004513039999665125, "count": 1, "is_parallel": true, "self": 0.0004513039999665125 }, "communicator.exchange": { "total": 0.08400220699991223, "count": 1, "is_parallel": true, "self": 0.08400220699991223 }, "steps_from_proto": { "total": 0.0022099390000676067, "count": 1, "is_parallel": true, "self": 0.0004049599999689235, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018049790000986832, "count": 10, "is_parallel": true, "self": 0.0018049790000986832 } } } } } } }, "UnityEnvironment.step": { "total": 284.19905628099457, "count": 18191, "is_parallel": true, "self": 13.467176656998959, "children": { "UnityEnvironment._generate_step_input": { "total": 7.627960425986657, "count": 18191, "is_parallel": true, "self": 7.627960425986657 }, "communicator.exchange": { "total": 221.42190232999496, "count": 18191, "is_parallel": true, "self": 221.42190232999496 }, "steps_from_proto": { "total": 41.68201686801399, "count": 18191, "is_parallel": true, "self": 8.15209339103626, "children": { "_process_rank_one_or_two_observation": { "total": 33.52992347697773, "count": 181910, "is_parallel": true, "self": 33.52992347697773 } } } } } } } } } } }, "trainer_advance": { "total": 160.4231340950248, "count": 18192, "self": 0.8122416120154412, "children": { "process_trajectory": { "total": 30.09176997000725, "count": 18192, "self": 29.6221062790072, "children": { "RLTrainer._checkpoint": { "total": 0.4696636910000507, "count": 4, "self": 0.4696636910000507 } } }, "_update_policy": { "total": 129.51912251300212, "count": 90, "self": 48.23629045700636, "children": { "TorchPPOOptimizer.update": { "total": 81.28283205599575, "count": 4587, "self": 81.28283205599575 } } } } } } }, "trainer_threads": { "total": 1.4919999102858128e-06, "count": 1, "self": 1.4919999102858128e-06 }, "TrainerController._save_models": { "total": 0.13127134299998033, "count": 1, "self": 0.0013563139998495899, "children": { "RLTrainer._checkpoint": { "total": 0.12991502900013074, "count": 1, "self": 0.12991502900013074 } } } } } } }