{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9257236123085022, "min": 0.9257236123085022, "max": 2.85087251663208, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8848.9921875, "min": 8848.9921875, "max": 29227.14453125, "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": 13.057461738586426, "min": 0.38897618651390076, "max": 13.057461738586426, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2546.205078125, "min": 75.46138000488281, "max": 2640.293701171875, "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": 0.06732053183876298, "min": 0.06322166504265339, "max": 0.0742530175035353, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2692821273550519, "min": 0.2605167574655235, "max": 0.35981430531155284, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.22601626988719492, "min": 0.13982274073778705, "max": 0.29387098704190817, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.9040650795487797, "min": 0.5592909629511482, "max": 1.3585495837763246, "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": 25.818181818181817, "min": 3.840909090909091, "max": 26.0, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1136.0, "min": 169.0, "max": 1411.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.818181818181817, "min": 3.840909090909091, "max": 26.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1136.0, "min": 169.0, "max": 1411.0, "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": "1700216438", "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": "1700216940" }, "total": 502.22486539500005, "count": 1, "self": 0.42500524199999745, "children": { "run_training.setup": { "total": 0.044669948999967346, "count": 1, "self": 0.044669948999967346 }, "TrainerController.start_learning": { "total": 501.7551902040001, "count": 1, "self": 0.6259564039945644, "children": { "TrainerController._reset_env": { "total": 8.176201995999918, "count": 1, "self": 8.176201995999918 }, "TrainerController.advance": { "total": 492.8657697680055, "count": 18200, "self": 0.3013136200193003, "children": { "env_step": { "total": 492.5644561479862, "count": 18200, "self": 340.4087428389854, "children": { "SubprocessEnvManager._take_step": { "total": 151.84856054499312, "count": 18200, "self": 1.5237474409943843, "children": { "TorchPolicy.evaluate": { "total": 150.32481310399874, "count": 18200, "self": 150.32481310399874 } } }, "workers": { "total": 0.30715276400769653, "count": 18200, "self": 0.0, "children": { "worker_root": { "total": 500.231713596996, "count": 18200, "is_parallel": true, "self": 242.62562280699456, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005502616999933707, "count": 1, "is_parallel": true, "self": 0.003849871999818788, "children": { "_process_rank_one_or_two_observation": { "total": 0.001652745000114919, "count": 10, "is_parallel": true, "self": 0.001652745000114919 } } }, "UnityEnvironment.step": { "total": 0.06710519199998544, "count": 1, "is_parallel": true, "self": 0.0006720140000879837, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004172659999994721, "count": 1, "is_parallel": true, "self": 0.0004172659999994721 }, "communicator.exchange": { "total": 0.06410648499991112, "count": 1, "is_parallel": true, "self": 0.06410648499991112 }, "steps_from_proto": { "total": 0.001909426999986863, "count": 1, "is_parallel": true, "self": 0.0003494110001156514, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015600159998712115, "count": 10, "is_parallel": true, "self": 0.0015600159998712115 } } } } } } }, "UnityEnvironment.step": { "total": 257.6060907900014, "count": 18199, "is_parallel": true, "self": 11.028681755007483, "children": { "UnityEnvironment._generate_step_input": { "total": 5.764600804994188, "count": 18199, "is_parallel": true, "self": 5.764600804994188 }, "communicator.exchange": { "total": 204.0870958390043, "count": 18199, "is_parallel": true, "self": 204.0870958390043 }, "steps_from_proto": { "total": 36.725712390995454, "count": 18199, "is_parallel": true, "self": 7.147675778994085, "children": { "_process_rank_one_or_two_observation": { "total": 29.57803661200137, "count": 181990, "is_parallel": true, "self": 29.57803661200137 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00012291200005165592, "count": 1, "self": 0.00012291200005165592, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 488.59221939203417, "count": 518912, "is_parallel": true, "self": 11.22611798205412, "children": { "process_trajectory": { "total": 278.8572700369805, "count": 518912, "is_parallel": true, "self": 277.5229314349805, "children": { "RLTrainer._checkpoint": { "total": 1.3343386020000025, "count": 4, "is_parallel": true, "self": 1.3343386020000025 } } }, "_update_policy": { "total": 198.50883137299957, "count": 90, "is_parallel": true, "self": 63.03522133899946, "children": { "TorchPPOOptimizer.update": { "total": 135.4736100340001, "count": 4587, "is_parallel": true, "self": 135.4736100340001 } } } } } } } } }, "TrainerController._save_models": { "total": 0.0871391240000321, "count": 1, "self": 0.0008231500000874803, "children": { "RLTrainer._checkpoint": { "total": 0.08631597399994462, "count": 1, "self": 0.08631597399994462 } } } } } } }