{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9813093543052673, "min": 0.9813093543052673, "max": 2.8593063354492188, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9380.3359375, "min": 9380.3359375, "max": 29282.15625, "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": 12.926692962646484, "min": 0.4476100206375122, "max": 12.944613456726074, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2520.705078125, "min": 86.83634185791016, "max": 2640.701171875, "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": 0.06827065329265429, "min": 0.0626948902375386, "max": 0.07488423440458171, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.27308261317061716, "min": 0.2507795609501544, "max": 0.36325468558032875, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.2012512924916604, "min": 0.13328136942764818, "max": 0.2734001470547096, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8050051699666416, "min": 0.5331254777105927, "max": 1.367000735273548, "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": 25.136363636363637, "min": 3.3863636363636362, "max": 25.727272727272727, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1106.0, "min": 149.0, "max": 1401.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.136363636363637, "min": 3.3863636363636362, "max": 25.727272727272727, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1106.0, "min": 149.0, "max": 1401.0, "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": "1698539822", "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": "1698540307" }, "total": 484.902829324, "count": 1, "self": 0.7397103269999548, "children": { "run_training.setup": { "total": 0.048127512000007755, "count": 1, "self": 0.048127512000007755 }, "TrainerController.start_learning": { "total": 484.114991485, "count": 1, "self": 0.5696455729924423, "children": { "TrainerController._reset_env": { "total": 8.320265462999998, "count": 1, "self": 8.320265462999998 }, "TrainerController.advance": { "total": 475.0731557270076, "count": 18206, "self": 0.28068115099495117, "children": { "env_step": { "total": 474.79247457601264, "count": 18206, "self": 323.18372905302675, "children": { "SubprocessEnvManager._take_step": { "total": 151.3227582400001, "count": 18206, "self": 1.5820389169896885, "children": { "TorchPolicy.evaluate": { "total": 149.7407193230104, "count": 18206, "self": 149.7407193230104 } } }, "workers": { "total": 0.28598728298578635, "count": 18206, "self": 0.0, "children": { "worker_root": { "total": 482.8042326879948, "count": 18206, "is_parallel": true, "self": 236.8716661629946, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005425838999997268, "count": 1, "is_parallel": true, "self": 0.0037910180000721994, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016348209999250685, "count": 10, "is_parallel": true, "self": 0.0016348209999250685 } } }, "UnityEnvironment.step": { "total": 0.04209001599997464, "count": 1, "is_parallel": true, "self": 0.000688771000000088, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002788499999724081, "count": 1, "is_parallel": true, "self": 0.0002788499999724081 }, "communicator.exchange": { "total": 0.03852463399999806, "count": 1, "is_parallel": true, "self": 0.03852463399999806 }, "steps_from_proto": { "total": 0.002597761000004084, "count": 1, "is_parallel": true, "self": 0.0005955419999850164, "children": { "_process_rank_one_or_two_observation": { "total": 0.0020022190000190676, "count": 10, "is_parallel": true, "self": 0.0020022190000190676 } } } } } } }, "UnityEnvironment.step": { "total": 245.9325665250002, "count": 18205, "is_parallel": true, "self": 10.941194027002098, "children": { "UnityEnvironment._generate_step_input": { "total": 5.786973521997652, "count": 18205, "is_parallel": true, "self": 5.786973521997652 }, "communicator.exchange": { "total": 192.50605124099735, "count": 18205, "is_parallel": true, "self": 192.50605124099735 }, "steps_from_proto": { "total": 36.6983477350031, "count": 18205, "is_parallel": true, "self": 6.94184765298769, "children": { "_process_rank_one_or_two_observation": { "total": 29.756500082015407, "count": 182050, "is_parallel": true, "self": 29.756500082015407 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0001524979999203424, "count": 1, "self": 0.0001524979999203424, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 471.028809040019, "count": 483287, "is_parallel": true, "self": 10.701201408025156, "children": { "process_trajectory": { "total": 268.61970322499354, "count": 483287, "is_parallel": true, "self": 267.87548050699337, "children": { "RLTrainer._checkpoint": { "total": 0.7442227180001737, "count": 4, "is_parallel": true, "self": 0.7442227180001737 } } }, "_update_policy": { "total": 191.70790440700029, "count": 90, "is_parallel": true, "self": 59.55379433499945, "children": { "TorchPPOOptimizer.update": { "total": 132.15411007200083, "count": 4587, "is_parallel": true, "self": 132.15411007200083 } } } } } } } } }, "TrainerController._save_models": { "total": 0.1517722240000694, "count": 1, "self": 0.0011104440001190596, "children": { "RLTrainer._checkpoint": { "total": 0.15066177999995034, "count": 1, "self": 0.15066177999995034 } } } } } } }