{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9972504377365112, "min": 0.9972504377365112, "max": 2.8695600032806396, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9532.716796875, "min": 9532.716796875, "max": 29387.1640625, "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": 12.032975196838379, "min": 0.22952815890312195, "max": 12.032975196838379, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2346.43017578125, "min": 44.52846145629883, "max": 2389.8583984375, "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.Losses.PolicyLoss.mean": { "value": 0.07278930435274436, "min": 0.06500586216234117, "max": 0.07375382571966232, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.29115721741097744, "min": 0.26002344864936466, "max": 0.3687691285983116, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20727698738668482, "min": 0.11384821428424294, "max": 0.2895725154993581, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8291079495467393, "min": 0.45539285713697175, "max": 1.4478625774967904, "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.CumulativeReward.mean": { "value": 24.636363636363637, "min": 3.340909090909091, "max": 24.636363636363637, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1084.0, "min": 147.0, "max": 1309.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.636363636363637, "min": 3.340909090909091, "max": 24.636363636363637, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1084.0, "min": 147.0, "max": 1309.0, "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": "1727346399", "python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ml-agents/config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.4.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1727347100" }, "total": 701.2455899700001, "count": 1, "self": 0.6470416089999844, "children": { "run_training.setup": { "total": 0.13579991400001745, "count": 1, "self": 0.13579991400001745 }, "TrainerController.start_learning": { "total": 700.4627484470001, "count": 1, "self": 1.1538475789999438, "children": { "TrainerController._reset_env": { "total": 3.677540264000072, "count": 1, "self": 3.677540264000072 }, "TrainerController.advance": { "total": 695.5252631580001, "count": 18202, "self": 0.5336557449816155, "children": { "env_step": { "total": 694.9916074130185, "count": 18202, "self": 534.4622109510157, "children": { "SubprocessEnvManager._take_step": { "total": 160.02029303399627, "count": 18202, "self": 3.3099695829664597, "children": { "TorchPolicy.evaluate": { "total": 156.7103234510298, "count": 18202, "self": 156.7103234510298 } } }, "workers": { "total": 0.5091034280065969, "count": 18202, "self": 0.0, "children": { "worker_root": { "total": 697.9829412490114, "count": 18202, "is_parallel": true, "self": 325.7715989030104, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0043478390000473155, "count": 1, "is_parallel": true, "self": 0.0015671840000095472, "children": { "_process_rank_one_or_two_observation": { "total": 0.0027806550000377683, "count": 10, "is_parallel": true, "self": 0.0027806550000377683 } } }, "UnityEnvironment.step": { "total": 0.055702397000004567, "count": 1, "is_parallel": true, "self": 0.0012367290000838693, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005974089999654097, "count": 1, "is_parallel": true, "self": 0.0005974089999654097 }, "communicator.exchange": { "total": 0.05072189099996649, "count": 1, "is_parallel": true, "self": 0.05072189099996649 }, "steps_from_proto": { "total": 0.0031463679999887972, "count": 1, "is_parallel": true, "self": 0.0005848919998925339, "children": { "_process_rank_one_or_two_observation": { "total": 0.0025614760000962633, "count": 10, "is_parallel": true, "self": 0.0025614760000962633 } } } } } } }, "UnityEnvironment.step": { "total": 372.21134234600106, "count": 18201, "is_parallel": true, "self": 18.10710557802804, "children": { "UnityEnvironment._generate_step_input": { "total": 8.819521410982134, "count": 18201, "is_parallel": true, "self": 8.819521410982134 }, "communicator.exchange": { "total": 295.46932162300254, "count": 18201, "is_parallel": true, "self": 295.46932162300254 }, "steps_from_proto": { "total": 49.815393733988344, "count": 18201, "is_parallel": true, "self": 10.323384889866816, "children": { "_process_rank_one_or_two_observation": { "total": 39.49200884412153, "count": 182010, "is_parallel": true, "self": 39.49200884412153 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00033191800002896343, "count": 1, "self": 0.00033191800002896343, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 687.3967931799235, "count": 910890, "is_parallel": true, "self": 21.281194166875935, "children": { "process_trajectory": { "total": 379.6217482920473, "count": 910890, "is_parallel": true, "self": 378.35388555104703, "children": { "RLTrainer._checkpoint": { "total": 1.2678627410002719, "count": 4, "is_parallel": true, "self": 1.2678627410002719 } } }, "_update_policy": { "total": 286.4938507210003, "count": 90, "is_parallel": true, "self": 77.34141165199765, "children": { "TorchPPOOptimizer.update": { "total": 209.15243906900264, "count": 4587, "is_parallel": true, "self": 209.15243906900264 } } } } } } } } }, "TrainerController._save_models": { "total": 0.10576552799989258, "count": 1, "self": 0.0017577529997652164, "children": { "RLTrainer._checkpoint": { "total": 0.10400777500012737, "count": 1, "self": 0.10400777500012737 } } } } } } }