{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.84107506275177, "min": 0.84107506275177, "max": 2.8714089393615723, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8030.58447265625, "min": 8030.58447265625, "max": 29437.685546875, "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": 13.00004768371582, "min": 0.31337860226631165, "max": 13.00004768371582, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2535.00927734375, "min": 60.795448303222656, "max": 2631.6298828125, "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": 0.06662663767173059, "min": 0.0616403974548174, "max": 0.07780870189818932, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.26650655068692236, "min": 0.26650655068692236, "max": 0.35447425805328997, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19852465968213828, "min": 0.13464574453503114, "max": 0.2961235759305019, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7940986387285531, "min": 0.5385829781401246, "max": 1.4806178796525096, "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": 25.5, "min": 3.909090909090909, "max": 25.763636363636362, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1122.0, "min": 172.0, "max": 1417.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.5, "min": 3.909090909090909, "max": 25.763636363636362, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1122.0, "min": 172.0, "max": 1417.0, "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": "1682217135", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[GCC 9.4.0]", "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": "1682217576" }, "total": 441.0332984209999, "count": 1, "self": 0.4358715629998642, "children": { "run_training.setup": { "total": 0.10756568099986907, "count": 1, "self": 0.10756568099986907 }, "TrainerController.start_learning": { "total": 440.4898611770002, "count": 1, "self": 0.5509106270169468, "children": { "TrainerController._reset_env": { "total": 3.8266570079999838, "count": 1, "self": 3.8266570079999838 }, "TrainerController.advance": { "total": 435.9842337479831, "count": 18201, "self": 0.26865080195011615, "children": { "env_step": { "total": 435.715582946033, "count": 18201, "self": 318.97517161602946, "children": { "SubprocessEnvManager._take_step": { "total": 116.48381639399986, "count": 18201, "self": 1.5624856200199702, "children": { "TorchPolicy.evaluate": { "total": 114.92133077397989, "count": 18201, "self": 114.92133077397989 } } }, "workers": { "total": 0.2565949360036939, "count": 18201, "self": 0.0, "children": { "worker_root": { "total": 439.09119377800835, "count": 18201, "is_parallel": true, "self": 204.09406672801447, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005029455000112648, "count": 1, "is_parallel": true, "self": 0.003645339000286185, "children": { "_process_rank_one_or_two_observation": { "total": 0.001384115999826463, "count": 10, "is_parallel": true, "self": 0.001384115999826463 } } }, "UnityEnvironment.step": { "total": 0.03254601100002219, "count": 1, "is_parallel": true, "self": 0.0005473169999277161, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00033557200003997423, "count": 1, "is_parallel": true, "self": 0.00033557200003997423 }, "communicator.exchange": { "total": 0.029945558000008532, "count": 1, "is_parallel": true, "self": 0.029945558000008532 }, "steps_from_proto": { "total": 0.001717564000045968, "count": 1, "is_parallel": true, "self": 0.0003529689997776586, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013645950002683094, "count": 10, "is_parallel": true, "self": 0.0013645950002683094 } } } } } } }, "UnityEnvironment.step": { "total": 234.99712704999388, "count": 18200, "is_parallel": true, "self": 9.503588366987515, "children": { "UnityEnvironment._generate_step_input": { "total": 5.168734869027503, "count": 18200, "is_parallel": true, "self": 5.168734869027503 }, "communicator.exchange": { "total": 190.19558744199549, "count": 18200, "is_parallel": true, "self": 190.19558744199549 }, "steps_from_proto": { "total": 30.129216371983375, "count": 18200, "is_parallel": true, "self": 5.85702417798143, "children": { "_process_rank_one_or_two_observation": { "total": 24.272192194001946, "count": 182000, "is_parallel": true, "self": 24.272192194001946 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0001266260001102637, "count": 1, "self": 0.0001266260001102637, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 432.70102066106097, "count": 389430, "is_parallel": true, "self": 9.36764324703745, "children": { "process_trajectory": { "total": 237.7769076980237, "count": 389430, "is_parallel": true, "self": 237.1151546890237, "children": { "RLTrainer._checkpoint": { "total": 0.6617530089999946, "count": 4, "is_parallel": true, "self": 0.6617530089999946 } } }, "_update_policy": { "total": 185.5564697159998, "count": 90, "is_parallel": true, "self": 68.60088044399913, "children": { "TorchPPOOptimizer.update": { "total": 116.95558927200068, "count": 4584, "is_parallel": true, "self": 116.95558927200068 } } } } } } } } }, "TrainerController._save_models": { "total": 0.12793316800002685, "count": 1, "self": 0.0009893559999909485, "children": { "RLTrainer._checkpoint": { "total": 0.1269438120000359, "count": 1, "self": 0.1269438120000359 } } } } } } }