{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9437726736068726, "min": 0.9437726736068726, "max": 2.875823974609375, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9000.759765625, "min": 9000.759765625, "max": 29451.314453125, "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": 13.210151672363281, "min": 0.41365987062454224, "max": 13.210151672363281, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2575.9794921875, "min": 80.25001525878906, "max": 2668.538330078125, "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": 0.07513870276264188, "min": 0.05882720539202459, "max": 0.07513870276264188, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.3005548110505675, "min": 0.23530882156809835, "max": 0.36215749583389684, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1940895297071513, "min": 0.10861266785821713, "max": 0.3091184555315504, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7763581188286052, "min": 0.43445067143286853, "max": 1.4009270802432414, "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": 26.136363636363637, "min": 3.159090909090909, "max": 26.163636363636364, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1150.0, "min": 139.0, "max": 1439.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 26.136363636363637, "min": 3.159090909090909, "max": 26.163636363636364, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1150.0, "min": 139.0, "max": 1439.0, "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": "1707159807", "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 --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": "2.2.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1707160265" }, "total": 457.52183259000003, "count": 1, "self": 0.4455861980000009, "children": { "run_training.setup": { "total": 0.05128259599996454, "count": 1, "self": 0.05128259599996454 }, "TrainerController.start_learning": { "total": 457.02496379600007, "count": 1, "self": 0.6270486329963205, "children": { "TrainerController._reset_env": { "total": 3.228359470999976, "count": 1, "self": 3.228359470999976 }, "TrainerController.advance": { "total": 453.0563310710038, "count": 18200, "self": 0.28339971103309836, "children": { "env_step": { "total": 452.7729313599707, "count": 18200, "self": 293.8548947089803, "children": { "SubprocessEnvManager._take_step": { "total": 158.60191928800623, "count": 18200, "self": 1.5173476920056146, "children": { "TorchPolicy.evaluate": { "total": 157.08457159600061, "count": 18200, "self": 157.08457159600061 } } }, "workers": { "total": 0.3161173629841869, "count": 18200, "self": 0.0, "children": { "worker_root": { "total": 455.8075109710055, "count": 18200, "is_parallel": true, "self": 227.7851270139979, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005612427999949432, "count": 1, "is_parallel": true, "self": 0.004083110000237866, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015293179997115658, "count": 10, "is_parallel": true, "self": 0.0015293179997115658 } } }, "UnityEnvironment.step": { "total": 0.03620067100018787, "count": 1, "is_parallel": true, "self": 0.0006744990000697726, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004326130001572892, "count": 1, "is_parallel": true, "self": 0.0004326130001572892 }, "communicator.exchange": { "total": 0.033123527000043396, "count": 1, "is_parallel": true, "self": 0.033123527000043396 }, "steps_from_proto": { "total": 0.00197003199991741, "count": 1, "is_parallel": true, "self": 0.0004575339999064454, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015124980000109645, "count": 10, "is_parallel": true, "self": 0.0015124980000109645 } } } } } } }, "UnityEnvironment.step": { "total": 228.0223839570076, "count": 18199, "is_parallel": true, "self": 10.931008968995911, "children": { "UnityEnvironment._generate_step_input": { "total": 5.382312677998925, "count": 18199, "is_parallel": true, "self": 5.382312677998925 }, "communicator.exchange": { "total": 177.82797039502088, "count": 18199, "is_parallel": true, "self": 177.82797039502088 }, "steps_from_proto": { "total": 33.881091914991885, "count": 18199, "is_parallel": true, "self": 6.5081054949225745, "children": { "_process_rank_one_or_two_observation": { "total": 27.37298642006931, "count": 181990, "is_parallel": true, "self": 27.37298642006931 } } } } } } } } } } } } }, "trainer_threads": { "total": 3.946199990423338e-05, "count": 1, "self": 3.946199990423338e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 447.8070153040942, "count": 684061, "is_parallel": true, "self": 13.918519254079229, "children": { "process_trajectory": { "total": 246.64140001901592, "count": 684061, "is_parallel": true, "self": 245.92595572801588, "children": { "RLTrainer._checkpoint": { "total": 0.7154442910000398, "count": 4, "is_parallel": true, "self": 0.7154442910000398 } } }, "_update_policy": { "total": 187.24709603099905, "count": 90, "is_parallel": true, "self": 50.966571411996256, "children": { "TorchPPOOptimizer.update": { "total": 136.2805246190028, "count": 4584, "is_parallel": true, "self": 136.2805246190028 } } } } } } } } }, "TrainerController._save_models": { "total": 0.11318515900006787, "count": 1, "self": 0.0011453220001840236, "children": { "RLTrainer._checkpoint": { "total": 0.11203983699988385, "count": 1, "self": 0.11203983699988385 } } } } } } }