{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0993940830230713, "min": 1.0993940830230713, "max": 2.849587917327881, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 10593.76171875, "min": 10593.76171875, "max": 29182.62890625, "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": 12.997933387756348, "min": 0.41111406683921814, "max": 12.997933387756348, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2534.596923828125, "min": 79.7561264038086, "max": 2625.916015625, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06669301109978537, "min": 0.06350136718352659, "max": 0.07365577957414858, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2667720443991415, "min": 0.25400546873410634, "max": 0.3682788978707429, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.21845597602134825, "min": 0.19031619467571667, "max": 0.33173991903370503, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.873823904085393, "min": 0.7694445433752501, "max": 1.658699595168525, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 8.082009730600007e-05, "min": 8.082009730600007e-05, "max": 0.0029188200027059994, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 0.00032328038922400026, "min": 0.00032328038922400026, "max": 0.013851600038280001, "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.CumulativeReward.mean": { "value": 25.704545454545453, "min": 3.1136363636363638, "max": 26.01818181818182, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1131.0, "min": 137.0, "max": 1431.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.704545454545453, "min": 3.1136363636363638, "max": 26.01818181818182, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1131.0, "min": 137.0, "max": 1431.0, "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": "1699522861", "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=SnowballTarget1 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.0+cu118", "numpy_version": "1.23.5", "end_time_seconds": "1699523340" }, "total": 478.6644258849999, "count": 1, "self": 0.8334502729999258, "children": { "run_training.setup": { "total": 0.0472272229999362, "count": 1, "self": 0.0472272229999362 }, "TrainerController.start_learning": { "total": 477.78374838900004, "count": 1, "self": 0.6059887159842674, "children": { "TrainerController._reset_env": { "total": 9.74358620199996, "count": 1, "self": 9.74358620199996 }, "TrainerController.advance": { "total": 467.26643971601584, "count": 18219, "self": 0.28543286201681894, "children": { "env_step": { "total": 466.981006853999, "count": 18219, "self": 317.50210353896694, "children": { "SubprocessEnvManager._take_step": { "total": 149.0738292030353, "count": 18219, "self": 1.4560226270159546, "children": { "TorchPolicy.evaluate": { "total": 147.61780657601935, "count": 18219, "self": 147.61780657601935 } } }, "workers": { "total": 0.40507411199678245, "count": 18219, "self": 0.0, "children": { "worker_root": { "total": 476.4099105159886, "count": 18219, "is_parallel": true, "self": 234.72466965399553, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005633177000049727, "count": 1, "is_parallel": true, "self": 0.004227479000178391, "children": { "_process_rank_one_or_two_observation": { "total": 0.001405697999871336, "count": 10, "is_parallel": true, "self": 0.001405697999871336 } } }, "UnityEnvironment.step": { "total": 0.04833833800000775, "count": 1, "is_parallel": true, "self": 0.00042770099992139876, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00033839100001387123, "count": 1, "is_parallel": true, "self": 0.00033839100001387123 }, "communicator.exchange": { "total": 0.04546880800000963, "count": 1, "is_parallel": true, "self": 0.04546880800000963 }, "steps_from_proto": { "total": 0.0021034380000628516, "count": 1, "is_parallel": true, "self": 0.0003881970001202717, "children": { "_process_rank_one_or_two_observation": { "total": 0.00171524099994258, "count": 10, "is_parallel": true, "self": 0.00171524099994258 } } } } } } }, "UnityEnvironment.step": { "total": 241.68524086199307, "count": 18218, "is_parallel": true, "self": 10.537795482017259, "children": { "UnityEnvironment._generate_step_input": { "total": 5.406722841982855, "count": 18218, "is_parallel": true, "self": 5.406722841982855 }, "communicator.exchange": { "total": 192.257302960993, "count": 18218, "is_parallel": true, "self": 192.257302960993 }, "steps_from_proto": { "total": 33.48341957699995, "count": 18218, "is_parallel": true, "self": 6.283872685011488, "children": { "_process_rank_one_or_two_observation": { "total": 27.19954689198846, "count": 182180, "is_parallel": true, "self": 27.19954689198846 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0001162339999609685, "count": 1, "self": 0.0001162339999609685, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 463.4752829500435, "count": 483054, "is_parallel": true, "self": 10.198586936065453, "children": { "process_trajectory": { "total": 263.1462121999783, "count": 483054, "is_parallel": true, "self": 261.7044838769783, "children": { "RLTrainer._checkpoint": { "total": 1.4417283230000066, "count": 4, "is_parallel": true, "self": 1.4417283230000066 } } }, "_update_policy": { "total": 190.13048381399972, "count": 90, "is_parallel": true, "self": 58.072666716006324, "children": { "TorchPPOOptimizer.update": { "total": 132.0578170979934, "count": 4587, "is_parallel": true, "self": 132.0578170979934 } } } } } } } } }, "TrainerController._save_models": { "total": 0.16761752100001104, "count": 1, "self": 0.002116115000035279, "children": { "RLTrainer._checkpoint": { "total": 0.16550140599997576, "count": 1, "self": 0.16550140599997576 } } } } } } }