{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9162722229957581, "min": 0.9162722229957581, "max": 2.852632999420166, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8708.2509765625, "min": 8708.2509765625, "max": 29119.677734375, "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": 12.742462158203125, "min": 0.44019535183906555, "max": 12.742462158203125, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2484.780029296875, "min": 85.39789581298828, "max": 2580.85205078125, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06639756204793801, "min": 0.06100237692636237, "max": 0.07360451979284156, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.26559024819175203, "min": 0.2440095077054495, "max": 0.35411339910648415, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20609476154341416, "min": 0.1396923542556846, "max": 0.290093705715502, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8243790461736566, "min": 0.5587694170227384, "max": 1.363314232697674, "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": 25.40909090909091, "min": 3.75, "max": 25.40909090909091, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1118.0, "min": 165.0, "max": 1369.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.40909090909091, "min": 3.75, "max": 25.40909090909091, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1118.0, "min": 165.0, "max": 1369.0, "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": "1741963060", "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": "1741963492" }, "total": 432.07542698399993, "count": 1, "self": 0.5584404939995693, "children": { "run_training.setup": { "total": 0.030052730000079464, "count": 1, "self": 0.030052730000079464 }, "TrainerController.start_learning": { "total": 431.4869337600003, "count": 1, "self": 0.3446839869941414, "children": { "TrainerController._reset_env": { "total": 3.469674556999962, "count": 1, "self": 3.469674556999962 }, "TrainerController.advance": { "total": 427.583158692006, "count": 18192, "self": 0.34814666200509237, "children": { "env_step": { "total": 305.7227951770044, "count": 18192, "self": 233.57209927000804, "children": { "SubprocessEnvManager._take_step": { "total": 71.94077298498269, "count": 18192, "self": 1.2662936080348572, "children": { "TorchPolicy.evaluate": { "total": 70.67447937694783, "count": 18192, "self": 70.67447937694783 } } }, "workers": { "total": 0.2099229220136749, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 429.9554564310138, "count": 18192, "is_parallel": true, "self": 224.59824960302853, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.011154239000006783, "count": 1, "is_parallel": true, "self": 0.009416278999879069, "children": { "_process_rank_one_or_two_observation": { "total": 0.001737960000127714, "count": 10, "is_parallel": true, "self": 0.001737960000127714 } } }, "UnityEnvironment.step": { "total": 0.06041906900009053, "count": 1, "is_parallel": true, "self": 0.0005724940001528012, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00039160400001492235, "count": 1, "is_parallel": true, "self": 0.00039160400001492235 }, "communicator.exchange": { "total": 0.05755808699996123, "count": 1, "is_parallel": true, "self": 0.05755808699996123 }, "steps_from_proto": { "total": 0.0018968839999615739, "count": 1, "is_parallel": true, "self": 0.00034249699979227444, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015543870001692994, "count": 10, "is_parallel": true, "self": 0.0015543870001692994 } } } } } } }, "UnityEnvironment.step": { "total": 205.35720682798524, "count": 18191, "is_parallel": true, "self": 9.724874797984057, "children": { "UnityEnvironment._generate_step_input": { "total": 5.688428061042259, "count": 18191, "is_parallel": true, "self": 5.688428061042259 }, "communicator.exchange": { "total": 157.76781769600166, "count": 18191, "is_parallel": true, "self": 157.76781769600166 }, "steps_from_proto": { "total": 32.176086272957264, "count": 18191, "is_parallel": true, "self": 5.703723577833216, "children": { "_process_rank_one_or_two_observation": { "total": 26.472362695124048, "count": 181910, "is_parallel": true, "self": 26.472362695124048 } } } } } } } } } } }, "trainer_advance": { "total": 121.51221685299652, "count": 18192, "self": 0.41311344700920927, "children": { "process_trajectory": { "total": 27.132865653987892, "count": 18192, "self": 26.586486358988395, "children": { "RLTrainer._checkpoint": { "total": 0.5463792949994968, "count": 4, "self": 0.5463792949994968 } } }, "_update_policy": { "total": 93.96623775199942, "count": 90, "self": 37.924850322991006, "children": { "TorchPPOOptimizer.update": { "total": 56.04138742900841, "count": 4587, "self": 56.04138742900841 } } } } } } }, "trainer_threads": { "total": 9.750001481734216e-07, "count": 1, "self": 9.750001481734216e-07 }, "TrainerController._save_models": { "total": 0.08941554900002302, "count": 1, "self": 0.000863553000272077, "children": { "RLTrainer._checkpoint": { "total": 0.08855199599975094, "count": 1, "self": 0.08855199599975094 } } } } } } }