{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.810502290725708, "min": 0.810502290725708, "max": 2.8695480823516846, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7738.67578125, "min": 7738.67578125, "max": 29639.5625, "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": 12.558168411254883, "min": 0.27872806787490845, "max": 12.558168411254883, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2448.8427734375, "min": 54.073246002197266, "max": 2558.234375, "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": 0.06977377677657048, "min": 0.06384657018683285, "max": 0.07849242166271413, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.27909510710628194, "min": 0.25586113828581336, "max": 0.36580883312055057, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.21766402630829343, "min": 0.1278085272471585, "max": 0.2801246593395869, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8706561052331737, "min": 0.511234108988634, "max": 1.4006232966979346, "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": 24.931818181818183, "min": 3.6136363636363638, "max": 24.931818181818183, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1097.0, "min": 159.0, "max": 1354.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.931818181818183, "min": 3.6136363636363638, "max": 24.931818181818183, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1097.0, "min": 159.0, "max": 1354.0, "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": "1711315390", "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 --force", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1711315870" }, "total": 479.48872910900013, "count": 1, "self": 0.528116946999944, "children": { "run_training.setup": { "total": 0.05035378600018703, "count": 1, "self": 0.05035378600018703 }, "TrainerController.start_learning": { "total": 478.910258376, "count": 1, "self": 0.6691899710094731, "children": { "TrainerController._reset_env": { "total": 2.2030564750000394, "count": 1, "self": 2.2030564750000394 }, "TrainerController.advance": { "total": 475.9434313819902, "count": 18200, "self": 0.3185010720039827, "children": { "env_step": { "total": 475.6249303099862, "count": 18200, "self": 308.2739972229831, "children": { "SubprocessEnvManager._take_step": { "total": 167.0125159070003, "count": 18200, "self": 1.629602177010156, "children": { "TorchPolicy.evaluate": { "total": 165.38291372999015, "count": 18200, "self": 165.38291372999015 } } }, "workers": { "total": 0.33841718000280707, "count": 18200, "self": 0.0, "children": { "worker_root": { "total": 477.4474657230048, "count": 18200, "is_parallel": true, "self": 236.23185046499157, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00240360500015413, "count": 1, "is_parallel": true, "self": 0.0006730550001066149, "children": { "_process_rank_one_or_two_observation": { "total": 0.001730550000047515, "count": 10, "is_parallel": true, "self": 0.001730550000047515 } } }, "UnityEnvironment.step": { "total": 0.08146709199991164, "count": 1, "is_parallel": true, "self": 0.0007704710001235071, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003517519999149954, "count": 1, "is_parallel": true, "self": 0.0003517519999149954 }, "communicator.exchange": { "total": 0.07571783299999879, "count": 1, "is_parallel": true, "self": 0.07571783299999879 }, "steps_from_proto": { "total": 0.0046270359998743515, "count": 1, "is_parallel": true, "self": 0.0003791089995957009, "children": { "_process_rank_one_or_two_observation": { "total": 0.004247927000278651, "count": 10, "is_parallel": true, "self": 0.004247927000278651 } } } } } } }, "UnityEnvironment.step": { "total": 241.21561525801326, "count": 18199, "is_parallel": true, "self": 10.79719044902231, "children": { "UnityEnvironment._generate_step_input": { "total": 5.904165682999746, "count": 18199, "is_parallel": true, "self": 5.904165682999746 }, "communicator.exchange": { "total": 187.95895233700912, "count": 18199, "is_parallel": true, "self": 187.95895233700912 }, "steps_from_proto": { "total": 36.55530678898208, "count": 18199, "is_parallel": true, "self": 7.072706220990312, "children": { "_process_rank_one_or_two_observation": { "total": 29.482600567991767, "count": 181990, "is_parallel": true, "self": 29.482600567991767 } } } } } } } } } } } } }, "trainer_threads": { "total": 4.150600011598726e-05, "count": 1, "self": 4.150600011598726e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 469.82119869396524, "count": 731393, "is_parallel": true, "self": 16.230413216978377, "children": { "process_trajectory": { "total": 259.5250741399864, "count": 731393, "is_parallel": true, "self": 258.9633462829863, "children": { "RLTrainer._checkpoint": { "total": 0.5617278570000508, "count": 4, "is_parallel": true, "self": 0.5617278570000508 } } }, "_update_policy": { "total": 194.0657113370005, "count": 90, "is_parallel": true, "self": 54.08591753099381, "children": { "TorchPPOOptimizer.update": { "total": 139.97979380600668, "count": 4587, "is_parallel": true, "self": 139.97979380600668 } } } } } } } } }, "TrainerController._save_models": { "total": 0.0945390420001786, "count": 1, "self": 0.0014298329999746784, "children": { "RLTrainer._checkpoint": { "total": 0.09310920900020392, "count": 1, "self": 0.09310920900020392 } } } } } } }