{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.7580826878547668, "min": 0.7580826878547668, "max": 2.8692173957824707, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7254.8515625, "min": 7254.8515625, "max": 29478.33984375, "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": 13.139311790466309, "min": 0.39720508456230164, "max": 13.139311790466309, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2562.165771484375, "min": 77.05778503417969, "max": 2662.35107421875, "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": 0.06884329452683839, "min": 0.061622042583693144, "max": 0.07567043418042457, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.27537317810735357, "min": 0.24648817033477258, "max": 0.37835217090212286, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.21491973175137652, "min": 0.1200501974021523, "max": 0.2817991497908153, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8596789270055061, "min": 0.4802007896086092, "max": 1.3401658625579347, "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": 26.045454545454547, "min": 3.4545454545454546, "max": 26.045454545454547, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1146.0, "min": 152.0, "max": 1415.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 26.045454545454547, "min": 3.4545454545454546, "max": 26.045454545454547, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1146.0, "min": 152.0, "max": 1415.0, "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": "1691783305", "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": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1691783899" }, "total": 594.10714609, "count": 1, "self": 0.6868097469999839, "children": { "run_training.setup": { "total": 0.05084278300000733, "count": 1, "self": 0.05084278300000733 }, "TrainerController.start_learning": { "total": 593.36949356, "count": 1, "self": 0.74096158399675, "children": { "TrainerController._reset_env": { "total": 6.346368761999997, "count": 1, "self": 6.346368761999997 }, "TrainerController.advance": { "total": 586.0224110990034, "count": 18214, "self": 0.3758246129937106, "children": { "env_step": { "total": 585.6465864860097, "count": 18214, "self": 433.0139128020242, "children": { "SubprocessEnvManager._take_step": { "total": 152.27059409499049, "count": 18214, "self": 2.157550592988514, "children": { "TorchPolicy.evaluate": { "total": 150.11304350200197, "count": 18214, "self": 150.11304350200197 } } }, "workers": { "total": 0.3620795889950159, "count": 18214, "self": 0.0, "children": { "worker_root": { "total": 590.8931135619987, "count": 18214, "is_parallel": true, "self": 272.4203420269946, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00697108299999627, "count": 1, "is_parallel": true, "self": 0.004363940000018829, "children": { "_process_rank_one_or_two_observation": { "total": 0.002607142999977441, "count": 10, "is_parallel": true, "self": 0.002607142999977441 } } }, "UnityEnvironment.step": { "total": 0.05010881399999789, "count": 1, "is_parallel": true, "self": 0.0007187100000578539, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003913029999580431, "count": 1, "is_parallel": true, "self": 0.0003913029999580431 }, "communicator.exchange": { "total": 0.046157507999964764, "count": 1, "is_parallel": true, "self": 0.046157507999964764 }, "steps_from_proto": { "total": 0.002841293000017231, "count": 1, "is_parallel": true, "self": 0.0004505560000325204, "children": { "_process_rank_one_or_two_observation": { "total": 0.0023907369999847106, "count": 10, "is_parallel": true, "self": 0.0023907369999847106 } } } } } } }, "UnityEnvironment.step": { "total": 318.4727715350041, "count": 18213, "is_parallel": true, "self": 13.152627139001595, "children": { "UnityEnvironment._generate_step_input": { "total": 6.4998642010037315, "count": 18213, "is_parallel": true, "self": 6.4998642010037315 }, "communicator.exchange": { "total": 252.90388440900028, "count": 18213, "is_parallel": true, "self": 252.90388440900028 }, "steps_from_proto": { "total": 45.916395785998475, "count": 18213, "is_parallel": true, "self": 8.70332095799489, "children": { "_process_rank_one_or_two_observation": { "total": 37.213074828003585, "count": 182130, "is_parallel": true, "self": 37.213074828003585 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00017514399996798602, "count": 1, "self": 0.00017514399996798602, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 581.0398586550169, "count": 556952, "is_parallel": true, "self": 13.325166906037907, "children": { "process_trajectory": { "total": 319.1320073359802, "count": 556952, "is_parallel": true, "self": 317.72466070298, "children": { "RLTrainer._checkpoint": { "total": 1.407346633000202, "count": 4, "is_parallel": true, "self": 1.407346633000202 } } }, "_update_policy": { "total": 248.5826844129989, "count": 90, "is_parallel": true, "self": 103.02125084699361, "children": { "TorchPPOOptimizer.update": { "total": 145.5614335660053, "count": 4587, "is_parallel": true, "self": 145.5614335660053 } } } } } } } } }, "TrainerController._save_models": { "total": 0.25957697099988764, "count": 1, "self": 0.0013094599999021739, "children": { "RLTrainer._checkpoint": { "total": 0.25826751099998546, "count": 1, "self": 0.25826751099998546 } } } } } } }