{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9202103614807129, "min": 0.9202103614807129, "max": 2.866475820541382, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8796.291015625, "min": 8796.291015625, "max": 29387.109375, "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": 12.823229789733887, "min": 0.5408574342727661, "max": 12.823229789733887, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2500.52978515625, "min": 104.92634582519531, "max": 2606.9072265625, "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": 0.06651720818512795, "min": 0.06235539605704081, "max": 0.07493936708630702, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2660688327405118, "min": 0.24942158422816324, "max": 0.3746968354315351, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.21687843080829172, "min": 0.13089671620971285, "max": 0.3080260164889635, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8675137232331669, "min": 0.5235868648388514, "max": 1.3896103434118572, "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": 25.227272727272727, "min": 3.5681818181818183, "max": 25.227272727272727, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1110.0, "min": 157.0, "max": 1381.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.227272727272727, "min": 3.5681818181818183, "max": 25.227272727272727, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1110.0, "min": 157.0, "max": 1381.0, "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": "1717142260", "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.x86_64 --run-id=SnowballTarget1 --no-graphics --force", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1717142712" }, "total": 452.33572795, "count": 1, "self": 0.42445379299999786, "children": { "run_training.setup": { "total": 0.05142919200000051, "count": 1, "self": 0.05142919200000051 }, "TrainerController.start_learning": { "total": 451.859844965, "count": 1, "self": 0.5632135549963095, "children": { "TrainerController._reset_env": { "total": 3.541285923000032, "count": 1, "self": 3.541285923000032 }, "TrainerController.advance": { "total": 447.66254705400377, "count": 18201, "self": 0.2694613340011074, "children": { "env_step": { "total": 447.39308572000266, "count": 18201, "self": 292.10742475000416, "children": { "SubprocessEnvManager._take_step": { "total": 155.01131487599037, "count": 18201, "self": 1.4396459539884745, "children": { "TorchPolicy.evaluate": { "total": 153.5716689220019, "count": 18201, "self": 153.5716689220019 } } }, "workers": { "total": 0.2743460940081377, "count": 18201, "self": 0.0, "children": { "worker_root": { "total": 450.55353015698563, "count": 18201, "is_parallel": true, "self": 228.1237831999797, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005615585999976247, "count": 1, "is_parallel": true, "self": 0.004052488000070298, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015630979999059491, "count": 10, "is_parallel": true, "self": 0.0015630979999059491 } } }, "UnityEnvironment.step": { "total": 0.03631462500004545, "count": 1, "is_parallel": true, "self": 0.0006571010002289768, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003906909998931951, "count": 1, "is_parallel": true, "self": 0.0003906909998931951 }, "communicator.exchange": { "total": 0.03335960799995519, "count": 1, "is_parallel": true, "self": 0.03335960799995519 }, "steps_from_proto": { "total": 0.0019072249999680935, "count": 1, "is_parallel": true, "self": 0.0003752309997935299, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015319940001745636, "count": 10, "is_parallel": true, "self": 0.0015319940001745636 } } } } } } }, "UnityEnvironment.step": { "total": 222.42974695700593, "count": 18200, "is_parallel": true, "self": 10.178511182994498, "children": { "UnityEnvironment._generate_step_input": { "total": 5.426610273012329, "count": 18200, "is_parallel": true, "self": 5.426610273012329 }, "communicator.exchange": { "total": 173.12294335198771, "count": 18200, "is_parallel": true, "self": 173.12294335198771 }, "steps_from_proto": { "total": 33.70168214901139, "count": 18200, "is_parallel": true, "self": 6.416058570024234, "children": { "_process_rank_one_or_two_observation": { "total": 27.285623578987156, "count": 182000, "is_parallel": true, "self": 27.285623578987156 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00011597200000323937, "count": 1, "self": 0.00011597200000323937, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 442.245792257072, "count": 676345, "is_parallel": true, "self": 13.722016242059453, "children": { "process_trajectory": { "total": 244.24036204901256, "count": 676345, "is_parallel": true, "self": 243.60425310201276, "children": { "RLTrainer._checkpoint": { "total": 0.6361089469997978, "count": 4, "is_parallel": true, "self": 0.6361089469997978 } } }, "_update_policy": { "total": 184.283413966, "count": 90, "is_parallel": true, "self": 59.40505667300238, "children": { "TorchPPOOptimizer.update": { "total": 124.87835729299763, "count": 4587, "is_parallel": true, "self": 124.87835729299763 } } } } } } } } }, "TrainerController._save_models": { "total": 0.09268246099986754, "count": 1, "self": 0.0009330109999154956, "children": { "RLTrainer._checkpoint": { "total": 0.09174944999995205, "count": 1, "self": 0.09174944999995205 } } } } } } }