{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9198384881019592, "min": 0.9198384881019592, "max": 2.8690733909606934, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8782.6181640625, "min": 8782.6181640625, "max": 29382.1796875, "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": 12.942930221557617, "min": 0.2794888913631439, "max": 12.942930221557617, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2523.871337890625, "min": 54.22084426879883, "max": 2602.950927734375, "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": 0.07495134262574663, "min": 0.06396080380940225, "max": 0.07495134262574663, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2998053705029865, "min": 0.2612323227476023, "max": 0.3570865439536397, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19461233424497584, "min": 0.09276995781179079, "max": 0.27108435223207755, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7784493369799034, "min": 0.37107983124716315, "max": 1.3373788665322697, "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": 25.90909090909091, "min": 2.8636363636363638, "max": 25.90909090909091, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1140.0, "min": 126.0, "max": 1419.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.90909090909091, "min": 2.8636363636363638, "max": 25.90909090909091, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1140.0, "min": 126.0, "max": 1419.0, "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": "1678034019", "python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \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": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.22.4", "end_time_seconds": "1678034466" }, "total": 447.13418132699996, "count": 1, "self": 0.3922857649998832, "children": { "run_training.setup": { "total": 0.11099902200004408, "count": 1, "self": 0.11099902200004408 }, "TrainerController.start_learning": { "total": 446.63089654000004, "count": 1, "self": 0.5251913389913057, "children": { "TrainerController._reset_env": { "total": 8.872696229000042, "count": 1, "self": 8.872696229000042 }, "TrainerController.advance": { "total": 437.11336933200863, "count": 18202, "self": 0.26747176200314016, "children": { "env_step": { "total": 436.8458975700055, "count": 18202, "self": 300.4721887299975, "children": { "SubprocessEnvManager._take_step": { "total": 136.11361653800185, "count": 18202, "self": 1.4448021290010615, "children": { "TorchPolicy.evaluate": { "total": 134.6688144090008, "count": 18202, "self": 30.25734530999665, "children": { "TorchPolicy.sample_actions": { "total": 104.41146909900414, "count": 18202, "self": 104.41146909900414 } } } } }, "workers": { "total": 0.26009230200611455, "count": 18202, "self": 0.0, "children": { "worker_root": { "total": 445.2543237829973, "count": 18202, "is_parallel": true, "self": 215.57725545598845, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0051117600000338825, "count": 1, "is_parallel": true, "self": 0.0037295900000344773, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013821699999994053, "count": 10, "is_parallel": true, "self": 0.0013821699999994053 } } }, "UnityEnvironment.step": { "total": 0.0380423479999763, "count": 1, "is_parallel": true, "self": 0.0003937429999609776, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00029105900000558904, "count": 1, "is_parallel": true, "self": 0.00029105900000558904 }, "communicator.exchange": { "total": 0.035698968000019704, "count": 1, "is_parallel": true, "self": 0.035698968000019704 }, "steps_from_proto": { "total": 0.0016585779999900296, "count": 1, "is_parallel": true, "self": 0.0003809189998946749, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012776590000953547, "count": 10, "is_parallel": true, "self": 0.0012776590000953547 } } } } } } }, "UnityEnvironment.step": { "total": 229.67706832700884, "count": 18201, "is_parallel": true, "self": 9.40379746600297, "children": { "UnityEnvironment._generate_step_input": { "total": 5.165627087002065, "count": 18201, "is_parallel": true, "self": 5.165627087002065 }, "communicator.exchange": { "total": 184.95797234699586, "count": 18201, "is_parallel": true, "self": 184.95797234699586 }, "steps_from_proto": { "total": 30.149671427007945, "count": 18201, "is_parallel": true, "self": 6.511740755001256, "children": { "_process_rank_one_or_two_observation": { "total": 23.63793067200669, "count": 182010, "is_parallel": true, "self": 23.63793067200669 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00011487400001897186, "count": 1, "self": 0.00011487400001897186, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 433.86321190902623, "count": 389324, "is_parallel": true, "self": 9.85751160304693, "children": { "process_trajectory": { "total": 249.72059568097882, "count": 389324, "is_parallel": true, "self": 248.58403401897874, "children": { "RLTrainer._checkpoint": { "total": 1.1365616620000765, "count": 4, "is_parallel": true, "self": 1.1365616620000765 } } }, "_update_policy": { "total": 174.28510462500049, "count": 90, "is_parallel": true, "self": 60.78995237999902, "children": { "TorchPPOOptimizer.update": { "total": 113.49515224500146, "count": 4587, "is_parallel": true, "self": 113.49515224500146 } } } } } } } } }, "TrainerController._save_models": { "total": 0.11952476600004047, "count": 1, "self": 0.0008330489999934798, "children": { "RLTrainer._checkpoint": { "total": 0.11869171700004699, "count": 1, "self": 0.11869171700004699 } } } } } } }