{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8184157609939575, "min": 0.8184157609939575, "max": 2.8416996002197266, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7778.2236328125, "min": 7778.2236328125, "max": 29008.0703125, "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": 13.101805686950684, "min": 0.24170830845832825, "max": 13.101805686950684, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2554.85205078125, "min": 46.89141082763672, "max": 2664.466796875, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.071978634556324, "min": 0.06133587086928767, "max": 0.07651697386741123, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.287914538225296, "min": 0.24534348347715068, "max": 0.36732271676181183, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20277833755986363, "min": 0.13464158196824, "max": 0.2896016617031658, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8111133502394545, "min": 0.53856632787296, "max": 1.3649795365099813, "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.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.Environment.CumulativeReward.mean": { "value": 25.818181818181817, "min": 3.590909090909091, "max": 26.295454545454547, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1136.0, "min": 158.0, "max": 1416.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.818181818181817, "min": 3.590909090909091, "max": 26.295454545454547, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1136.0, "min": 158.0, "max": 1416.0, "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": "1739154102", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1739154546" }, "total": 443.266756104, "count": 1, "self": 0.4380346839999447, "children": { "run_training.setup": { "total": 0.023333783999987645, "count": 1, "self": 0.023333783999987645 }, "TrainerController.start_learning": { "total": 442.8053876360001, "count": 1, "self": 0.3992177759930655, "children": { "TrainerController._reset_env": { "total": 3.1985911759999226, "count": 1, "self": 3.1985911759999226 }, "TrainerController.advance": { "total": 439.1181710490072, "count": 18192, "self": 0.4055515380214274, "children": { "env_step": { "total": 311.4119687969883, "count": 18192, "self": 237.59036189998676, "children": { "SubprocessEnvManager._take_step": { "total": 73.58102036899959, "count": 18192, "self": 1.3147089810007628, "children": { "TorchPolicy.evaluate": { "total": 72.26631138799883, "count": 18192, "self": 72.26631138799883 } } }, "workers": { "total": 0.24058652800192704, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 441.1300303900018, "count": 18192, "is_parallel": true, "self": 233.8275401670013, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0062181449999343386, "count": 1, "is_parallel": true, "self": 0.004707150999934129, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015109940000002098, "count": 10, "is_parallel": true, "self": 0.0015109940000002098 } } }, "UnityEnvironment.step": { "total": 0.035637715999996544, "count": 1, "is_parallel": true, "self": 0.0006001840000635639, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00047035599993705546, "count": 1, "is_parallel": true, "self": 0.00047035599993705546 }, "communicator.exchange": { "total": 0.03277034500001719, "count": 1, "is_parallel": true, "self": 0.03277034500001719 }, "steps_from_proto": { "total": 0.001796830999978738, "count": 1, "is_parallel": true, "self": 0.00036910500000431057, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014277259999744274, "count": 10, "is_parallel": true, "self": 0.0014277259999744274 } } } } } } }, "UnityEnvironment.step": { "total": 207.30249022300052, "count": 18191, "is_parallel": true, "self": 9.77020842100137, "children": { "UnityEnvironment._generate_step_input": { "total": 5.294312684997408, "count": 18191, "is_parallel": true, "self": 5.294312684997408 }, "communicator.exchange": { "total": 160.9824902189947, "count": 18191, "is_parallel": true, "self": 160.9824902189947 }, "steps_from_proto": { "total": 31.255478898007027, "count": 18191, "is_parallel": true, "self": 5.62673078499904, "children": { "_process_rank_one_or_two_observation": { "total": 25.628748113007987, "count": 181910, "is_parallel": true, "self": 25.628748113007987 } } } } } } } } } } }, "trainer_advance": { "total": 127.30065071399747, "count": 18192, "self": 0.5373614759939755, "children": { "process_trajectory": { "total": 27.47561059300358, "count": 18192, "self": 26.84851138600368, "children": { "RLTrainer._checkpoint": { "total": 0.6270992069999011, "count": 4, "self": 0.6270992069999011 } } }, "_update_policy": { "total": 99.28767864499991, "count": 90, "self": 40.35185329600017, "children": { "TorchPPOOptimizer.update": { "total": 58.93582534899974, "count": 4587, "self": 58.93582534899974 } } } } } } }, "trainer_threads": { "total": 9.48999968386488e-07, "count": 1, "self": 9.48999968386488e-07 }, "TrainerController._save_models": { "total": 0.08940668599996116, "count": 1, "self": 0.0009491040000284556, "children": { "RLTrainer._checkpoint": { "total": 0.0884575819999327, "count": 1, "self": 0.0884575819999327 } } } } } } }