{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8768581748008728, "min": 0.864930272102356, "max": 2.8430848121643066, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8362.5966796875, "min": 8362.5966796875, "max": 29116.03125, "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": 13.190998077392578, "min": 0.3260194957256317, "max": 13.190998077392578, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2572.24462890625, "min": 63.247779846191406, "max": 2665.80517578125, "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": 0.07307105794418876, "min": 0.06372162994036142, "max": 0.07488110149712941, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.29228423177675505, "min": 0.2631797922253563, "max": 0.37440550748564705, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1944066449342405, "min": 0.13384963994087906, "max": 0.299617010939355, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.777626579736962, "min": 0.5353985597635162, "max": 1.498085054696775, "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": 25.477272727272727, "min": 3.5, "max": 26.09090909090909, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1121.0, "min": 154.0, "max": 1435.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.477272727272727, "min": 3.5, "max": 26.09090909090909, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1121.0, "min": 154.0, "max": 1435.0, "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": "1723096357", "python_version": "3.10.12 (main, Jul 29 2024, 16:56:48) [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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1723096815" }, "total": 458.4854244200001, "count": 1, "self": 0.3895158880000622, "children": { "run_training.setup": { "total": 0.05996051400001079, "count": 1, "self": 0.05996051400001079 }, "TrainerController.start_learning": { "total": 458.035948018, "count": 1, "self": 0.5920743620031317, "children": { "TrainerController._reset_env": { "total": 2.7681922689999965, "count": 1, "self": 2.7681922689999965 }, "TrainerController.advance": { "total": 454.58274762599694, "count": 18200, "self": 0.28110321999241705, "children": { "env_step": { "total": 454.3016444060045, "count": 18200, "self": 294.6073156170104, "children": { "SubprocessEnvManager._take_step": { "total": 159.38401260299372, "count": 18200, "self": 1.5155030309959443, "children": { "TorchPolicy.evaluate": { "total": 157.86850957199778, "count": 18200, "self": 157.86850957199778 } } }, "workers": { "total": 0.31031618600039224, "count": 18200, "self": 0.0, "children": { "worker_root": { "total": 456.78867824201257, "count": 18200, "is_parallel": true, "self": 229.87676893901653, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005299108999992086, "count": 1, "is_parallel": true, "self": 0.003707722000058311, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015913869999337749, "count": 10, "is_parallel": true, "self": 0.0015913869999337749 } } }, "UnityEnvironment.step": { "total": 0.036934653999992406, "count": 1, "is_parallel": true, "self": 0.0006639049999819235, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00040254900000036287, "count": 1, "is_parallel": true, "self": 0.00040254900000036287 }, "communicator.exchange": { "total": 0.03392950200000655, "count": 1, "is_parallel": true, "self": 0.03392950200000655 }, "steps_from_proto": { "total": 0.0019386980000035692, "count": 1, "is_parallel": true, "self": 0.00037705799996956557, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015616400000340036, "count": 10, "is_parallel": true, "self": 0.0015616400000340036 } } } } } } }, "UnityEnvironment.step": { "total": 226.91190930299604, "count": 18199, "is_parallel": true, "self": 10.264438682986281, "children": { "UnityEnvironment._generate_step_input": { "total": 5.349243692005018, "count": 18199, "is_parallel": true, "self": 5.349243692005018 }, "communicator.exchange": { "total": 176.88062035800644, "count": 18199, "is_parallel": true, "self": 176.88062035800644 }, "steps_from_proto": { "total": 34.4176065699983, "count": 18199, "is_parallel": true, "self": 6.672299461959653, "children": { "_process_rank_one_or_two_observation": { "total": 27.745307108038645, "count": 181990, "is_parallel": true, "self": 27.745307108038645 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00018427199995585397, "count": 1, "self": 0.00018427199995585397, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 448.9035167119987, "count": 681514, "is_parallel": true, "self": 14.208710791987642, "children": { "process_trajectory": { "total": 249.2056527800106, "count": 681514, "is_parallel": true, "self": 248.24926487001056, "children": { "RLTrainer._checkpoint": { "total": 0.9563879100000463, "count": 4, "is_parallel": true, "self": 0.9563879100000463 } } }, "_update_policy": { "total": 185.4891531400004, "count": 90, "is_parallel": true, "self": 56.71600624600248, "children": { "TorchPPOOptimizer.update": { "total": 128.77314689399793, "count": 4587, "is_parallel": true, "self": 128.77314689399793 } } } } } } } } }, "TrainerController._save_models": { "total": 0.09274948899997071, "count": 1, "self": 0.0009566349999658996, "children": { "RLTrainer._checkpoint": { "total": 0.09179285400000481, "count": 1, "self": 0.09179285400000481 } } } } } } }