{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.5860854387283325, "min": 0.5860854387283325, "max": 2.443842887878418, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 29282.001953125, "min": 29282.001953125, "max": 123658.453125, "count": 20 }, "SnowballTarget.Step.mean": { "value": 999952.0, "min": 49952.0, "max": 999952.0, "count": 20 }, "SnowballTarget.Step.sum": { "value": 999952.0, "min": 49952.0, "max": 999952.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 14.130938529968262, "min": 3.2179858684539795, "max": 14.170147895812988, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 7051.33837890625, "min": 1599.3389892578125, "max": 7113.4140625, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 48158.0, "min": 48158.0, "max": 50347.0, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 27.798387096774192, "min": 10.15983606557377, "max": 27.8300395256917, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 6894.0, "min": 2479.0, "max": 7041.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 27.798387096774192, "min": 10.15983606557377, "max": 27.8300395256917, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 6894.0, "min": 2479.0, "max": 7041.0, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07071791908982689, "min": 0.06703672302408809, "max": 0.07201141945276286, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 1.6265121390660184, "min": 1.474807906529938, "max": 1.6562626474135458, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.17576968430431092, "min": 0.1658779936004986, "max": 0.2771722643881503, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 4.042702738999151, "min": 3.8151938528114675, "max": 6.374962080927457, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 7.620097460000001e-06, "min": 7.620097460000001e-06, "max": 0.0002924109843478546, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 0.00017526224158, "min": 0.00017526224158, "max": 0.006433041655652801, "count": 20 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10254, "min": 0.10254, "max": 0.1974703272727273, "count": 20 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 2.35842, "min": 2.35842, "max": 4.427960000000001, "count": 20 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.000136746, "min": 0.000136746, "max": 0.004873769330909091, "count": 20 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0031451580000000003, "min": 0.0031451580000000003, "max": 0.10722292527999999, "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": "1698231368", "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=SnowballTarget2 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.0+cu118", "numpy_version": "1.23.5", "end_time_seconds": "1698233609" }, "total": 2241.1600546160003, "count": 1, "self": 0.4240094830001908, "children": { "run_training.setup": { "total": 0.042658243000005314, "count": 1, "self": 0.042658243000005314 }, "TrainerController.start_learning": { "total": 2240.69338689, "count": 1, "self": 2.80471784100655, "children": { "TrainerController._reset_env": { "total": 3.1852731500000573, "count": 1, "self": 3.1852731500000573 }, "TrainerController.advance": { "total": 2234.5915062999934, "count": 90954, "self": 1.3369565009556936, "children": { "env_step": { "total": 2233.2545497990377, "count": 90954, "self": 1437.3404762530213, "children": { "SubprocessEnvManager._take_step": { "total": 794.511444212965, "count": 90954, "self": 7.143909519008162, "children": { "TorchPolicy.evaluate": { "total": 787.3675346939568, "count": 90954, "self": 787.3675346939568 } } }, "workers": { "total": 1.4026293330514363, "count": 90954, "self": 0.0, "children": { "worker_root": { "total": 2234.3299840999957, "count": 90954, "is_parallel": true, "self": 1030.1527709440015, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0020364339999332515, "count": 1, "is_parallel": true, "self": 0.0006503330001805807, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013861009997526708, "count": 10, "is_parallel": true, "self": 0.0013861009997526708 } } }, "UnityEnvironment.step": { "total": 0.0351438180000514, "count": 1, "is_parallel": true, "self": 0.0006059190000087256, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000343800999985433, "count": 1, "is_parallel": true, "self": 0.000343800999985433 }, "communicator.exchange": { "total": 0.0323127190000605, "count": 1, "is_parallel": true, "self": 0.0323127190000605 }, "steps_from_proto": { "total": 0.0018813789999967412, "count": 1, "is_parallel": true, "self": 0.000367557000117813, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015138219998789282, "count": 10, "is_parallel": true, "self": 0.0015138219998789282 } } } } } } }, "UnityEnvironment.step": { "total": 1204.1772131559942, "count": 90953, "is_parallel": true, "self": 52.74599389899549, "children": { "UnityEnvironment._generate_step_input": { "total": 27.691112145988882, "count": 90953, "is_parallel": true, "self": 27.691112145988882 }, "communicator.exchange": { "total": 948.1140495010205, "count": 90953, "is_parallel": true, "self": 948.1140495010205 }, "steps_from_proto": { "total": 175.62605760998918, "count": 90953, "is_parallel": true, "self": 32.82275263505085, "children": { "_process_rank_one_or_two_observation": { "total": 142.80330497493833, "count": 909530, "is_parallel": true, "self": 142.80330497493833 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00027903399995921063, "count": 1, "self": 0.00027903399995921063, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 2221.978957164012, "count": 1644593, "is_parallel": true, "self": 35.98496506884294, "children": { "process_trajectory": { "total": 932.611493342173, "count": 1644593, "is_parallel": true, "self": 928.8194726101746, "children": { "RLTrainer._checkpoint": { "total": 3.792020731998491, "count": 20, "is_parallel": true, "self": 3.792020731998491 } } }, "_update_policy": { "total": 1253.382498752996, "count": 454, "is_parallel": true, "self": 324.37970300498364, "children": { "TorchPPOOptimizer.update": { "total": 929.0027957480124, "count": 23151, "is_parallel": true, "self": 929.0027957480124 } } } } } } } } }, "TrainerController._save_models": { "total": 0.11161056500031918, "count": 1, "self": 0.0015727760005574964, "children": { "RLTrainer._checkpoint": { "total": 0.11003778899976169, "count": 1, "self": 0.11003778899976169 } } } } } } }