{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.6212834715843201, "min": 0.6212834715843201, "max": 2.5113227367401123, "count": 10 }, "SnowballTarget.Policy.Entropy.sum": { "value": 31334.431640625, "min": 31334.431640625, "max": 127100.5546875, "count": 10 }, "SnowballTarget.Step.mean": { "value": 499912.0, "min": 49952.0, "max": 499912.0, "count": 10 }, "SnowballTarget.Step.sum": { "value": 499912.0, "min": 49952.0, "max": 499912.0, "count": 10 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 13.776063919067383, "min": 3.122358560562134, "max": 13.776063919067383, "count": 10 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 6901.80810546875, "min": 1551.812255859375, "max": 6901.80810546875, "count": 10 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 10 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 50347.0, "min": 48158.0, "max": 50347.0, "count": 10 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 26.972332015810277, "min": 9.692622950819672, "max": 26.972332015810277, "count": 10 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 6824.0, "min": 2365.0, "max": 6824.0, "count": 10 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 26.972332015810277, "min": 9.692622950819672, "max": 26.972332015810277, "count": 10 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 6824.0, "min": 2365.0, "max": 6824.0, "count": 10 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06727982555731091, "min": 0.06610792550520869, "max": 0.06946593991671618, "count": 10 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 1.547435987818151, "min": 1.4543743611145912, "max": 1.5977166180844722, "count": 10 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.18281737867447423, "min": 0.18281737867447423, "max": 0.2537367838194303, "count": 10 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 4.2047997095129075, "min": 4.2047997095129075, "max": 5.835946027846897, "count": 10 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 1.488009504e-05, "min": 1.488009504e-05, "max": 0.00028482000505999997, "count": 10 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 0.00034224218592, "min": 0.00034224218592, "max": 0.006266040111319999, "count": 10 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10496000000000003, "min": 0.10496000000000003, "max": 0.19493999999999997, "count": 10 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 2.4140800000000007, "min": 2.4140800000000007, "max": 4.288679999999999, "count": 10 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.00025750400000000003, "min": 0.00025750400000000003, "max": 0.004747505999999999, "count": 10 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.005922592000000001, "min": 0.005922592000000001, "max": 0.104445132, "count": 10 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 10 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 10 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1703599484", "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": "2.1.2+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1703600573" }, "total": 1089.957315092, "count": 1, "self": 0.7371019600000182, "children": { "run_training.setup": { "total": 0.05031633300006888, "count": 1, "self": 0.05031633300006888 }, "TrainerController.start_learning": { "total": 1089.169896799, "count": 1, "self": 1.4554743249784678, "children": { "TrainerController._reset_env": { "total": 2.7857125090000636, "count": 1, "self": 2.7857125090000636 }, "TrainerController.advance": { "total": 1084.7899431570218, "count": 45548, "self": 0.6593831560323906, "children": { "env_step": { "total": 1084.1305600009894, "count": 45548, "self": 686.7062443009918, "children": { "SubprocessEnvManager._take_step": { "total": 396.7267661689973, "count": 45548, "self": 3.706804077967263, "children": { "TorchPolicy.evaluate": { "total": 393.01996209103004, "count": 45548, "self": 393.01996209103004 } } }, "workers": { "total": 0.6975495310002771, "count": 45548, "self": 0.0, "children": { "worker_root": { "total": 1085.8218655810106, "count": 45548, "is_parallel": true, "self": 515.967000327981, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004778807000093366, "count": 1, "is_parallel": true, "self": 0.0032336840000652955, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015451230000280702, "count": 10, "is_parallel": true, "self": 0.0015451230000280702 } } }, "UnityEnvironment.step": { "total": 0.03785008199997719, "count": 1, "is_parallel": true, "self": 0.0007229389999565683, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00041126500002519606, "count": 1, "is_parallel": true, "self": 0.00041126500002519606 }, "communicator.exchange": { "total": 0.034826715000008335, "count": 1, "is_parallel": true, "self": 0.034826715000008335 }, "steps_from_proto": { "total": 0.001889162999987093, "count": 1, "is_parallel": true, "self": 0.00036270800023885386, "children": { "_process_rank_one_or_two_observation": { "total": 0.001526454999748239, "count": 10, "is_parallel": true, "self": 0.001526454999748239 } } } } } } }, "UnityEnvironment.step": { "total": 569.8548652530295, "count": 45547, "is_parallel": true, "self": 26.79547779401105, "children": { "UnityEnvironment._generate_step_input": { "total": 13.565955926022298, "count": 45547, "is_parallel": true, "self": 13.565955926022298 }, "communicator.exchange": { "total": 444.3168439539992, "count": 45547, "is_parallel": true, "self": 444.3168439539992 }, "steps_from_proto": { "total": 85.17658757899699, "count": 45547, "is_parallel": true, "self": 15.796277885033192, "children": { "_process_rank_one_or_two_observation": { "total": 69.3803096939638, "count": 455470, "is_parallel": true, "self": 69.3803096939638 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.000761173000000781, "count": 1, "self": 0.000761173000000781, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 1074.2896445499428, "count": 1352597, "is_parallel": true, "self": 28.35052806101112, "children": { "process_trajectory": { "total": 489.1180842299324, "count": 1352597, "is_parallel": true, "self": 486.46477100393224, "children": { "RLTrainer._checkpoint": { "total": 2.6533132260001366, "count": 10, "is_parallel": true, "self": 2.6533132260001366 } } }, "_update_policy": { "total": 556.8210322589994, "count": 227, "is_parallel": true, "self": 154.71368056399308, "children": { "TorchPPOOptimizer.update": { "total": 402.1073516950063, "count": 11574, "is_parallel": true, "self": 402.1073516950063 } } } } } } } } }, "TrainerController._save_models": { "total": 0.13800563499989948, "count": 1, "self": 0.0013383019997945667, "children": { "RLTrainer._checkpoint": { "total": 0.13666733300010492, "count": 1, "self": 0.13666733300010492 } } } } } } }