{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.017451524734497, "min": 1.017451524734497, "max": 2.8791980743408203, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9714.626953125, "min": 9714.626953125, "max": 29517.5390625, "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": 12.798436164855957, "min": 0.2849070429801941, "max": 12.798436164855957, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2495.695068359375, "min": 55.27196502685547, "max": 2578.334228515625, "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": 0.06852145218270414, "min": 0.06266230287014075, "max": 0.07916880658840277, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.27408580873081656, "min": 0.250649211480563, "max": 0.3678228515394342, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.21902749680128752, "min": 0.09066353674621924, "max": 0.28132632941591973, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8761099872051501, "min": 0.36265414698487697, "max": 1.4066316470795988, "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": 25.204545454545453, "min": 2.6818181818181817, "max": 25.204545454545453, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1109.0, "min": 118.0, "max": 1373.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.204545454545453, "min": 2.6818181818181817, "max": 25.204545454545453, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1109.0, "min": 118.0, "max": 1373.0, "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": "1698518000", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "2.1.0+cu118", "numpy_version": "1.23.5", "end_time_seconds": "1698518472" }, "total": 471.49469264699997, "count": 1, "self": 0.42846041099994636, "children": { "run_training.setup": { "total": 0.06715131400000018, "count": 1, "self": 0.06715131400000018 }, "TrainerController.start_learning": { "total": 470.999080922, "count": 1, "self": 0.5379021229971386, "children": { "TrainerController._reset_env": { "total": 8.23735443999999, "count": 1, "self": 8.23735443999999 }, "TrainerController.advance": { "total": 462.1377211970029, "count": 18199, "self": 0.26061075200061623, "children": { "env_step": { "total": 461.8771104450023, "count": 18199, "self": 315.1225336110016, "children": { "SubprocessEnvManager._take_step": { "total": 146.47266273699768, "count": 18199, "self": 1.4319829239989872, "children": { "TorchPolicy.evaluate": { "total": 145.0406798129987, "count": 18199, "self": 145.0406798129987 } } }, "workers": { "total": 0.28191409700303893, "count": 18199, "self": 0.0, "children": { "worker_root": { "total": 469.8504369159892, "count": 18199, "is_parallel": true, "self": 230.73708401599197, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005554617000029793, "count": 1, "is_parallel": true, "self": 0.0035072420000688, "children": { "_process_rank_one_or_two_observation": { "total": 0.0020473749999609936, "count": 10, "is_parallel": true, "self": 0.0020473749999609936 } } }, "UnityEnvironment.step": { "total": 0.04912546299999576, "count": 1, "is_parallel": true, "self": 0.0006825980000257914, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003754749999984597, "count": 1, "is_parallel": true, "self": 0.0003754749999984597 }, "communicator.exchange": { "total": 0.04615131099996006, "count": 1, "is_parallel": true, "self": 0.04615131099996006 }, "steps_from_proto": { "total": 0.0019160790000114503, "count": 1, "is_parallel": true, "self": 0.00037110599998868565, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015449730000227646, "count": 10, "is_parallel": true, "self": 0.0015449730000227646 } } } } } } }, "UnityEnvironment.step": { "total": 239.1133528999972, "count": 18198, "is_parallel": true, "self": 10.597959162002212, "children": { "UnityEnvironment._generate_step_input": { "total": 5.6059140030045, "count": 18198, "is_parallel": true, "self": 5.6059140030045 }, "communicator.exchange": { "total": 187.61082248400157, "count": 18198, "is_parallel": true, "self": 187.61082248400157 }, "steps_from_proto": { "total": 35.298657250988924, "count": 18198, "is_parallel": true, "self": 6.681868387978625, "children": { "_process_rank_one_or_two_observation": { "total": 28.6167888630103, "count": 181980, "is_parallel": true, "self": 28.6167888630103 } } } } } } } } } } } } }, "trainer_threads": { "total": 3.53789999962828e-05, "count": 1, "self": 3.53789999962828e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 458.28027237094216, "count": 477761, "is_parallel": true, "self": 10.197087138913105, "children": { "process_trajectory": { "total": 260.7348401320289, "count": 477761, "is_parallel": true, "self": 260.1972922530289, "children": { "RLTrainer._checkpoint": { "total": 0.5375478790000443, "count": 4, "is_parallel": true, "self": 0.5375478790000443 } } }, "_update_policy": { "total": 187.34834510000013, "count": 90, "is_parallel": true, "self": 57.70202621699946, "children": { "TorchPPOOptimizer.update": { "total": 129.64631888300067, "count": 4584, "is_parallel": true, "self": 129.64631888300067 } } } } } } } } }, "TrainerController._save_models": { "total": 0.08606778299997586, "count": 1, "self": 0.0007941159999518277, "children": { "RLTrainer._checkpoint": { "total": 0.08527366700002403, "count": 1, "self": 0.08527366700002403 } } } } } } }