{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0313820838928223, "min": 1.0183372497558594, "max": 2.86647367477417, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9881.671875, "min": 9881.671875, "max": 29387.087890625, "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": 12.68883991241455, "min": 0.35565751791000366, "max": 12.68883991241455, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2474.32373046875, "min": 68.99755859375, "max": 2569.96484375, "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": 0.06892985248943626, "min": 0.06016082922009196, "max": 0.07450246922442103, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.275719409957745, "min": 0.2486872403212735, "max": 0.3574929504573126, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.21388083374967762, "min": 0.10653519304697492, "max": 0.28840743523894574, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8555233349987105, "min": 0.4261407721878997, "max": 1.3782376977158528, "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": 25.318181818181817, "min": 2.8863636363636362, "max": 25.436363636363637, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1114.0, "min": 127.0, "max": 1399.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.318181818181817, "min": 2.8863636363636362, "max": 25.436363636363637, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1114.0, "min": 127.0, "max": 1399.0, "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": "1698559376", "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": "1698559878" }, "total": 501.732813698, "count": 1, "self": 0.4262692010000251, "children": { "run_training.setup": { "total": 0.043849070000021584, "count": 1, "self": 0.043849070000021584 }, "TrainerController.start_learning": { "total": 501.2626954269999, "count": 1, "self": 0.614193753999416, "children": { "TrainerController._reset_env": { "total": 8.368119120000017, "count": 1, "self": 8.368119120000017 }, "TrainerController.advance": { "total": 492.19210148700046, "count": 18202, "self": 0.3117935090076571, "children": { "env_step": { "total": 491.8803079779928, "count": 18202, "self": 336.50764899799645, "children": { "SubprocessEnvManager._take_step": { "total": 155.05216970198938, "count": 18202, "self": 1.5226202689793809, "children": { "TorchPolicy.evaluate": { "total": 153.52954943301, "count": 18202, "self": 153.52954943301 } } }, "workers": { "total": 0.3204892780069599, "count": 18202, "self": 0.0, "children": { "worker_root": { "total": 499.9500207240042, "count": 18202, "is_parallel": true, "self": 243.61799014701006, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005562591000000339, "count": 1, "is_parallel": true, "self": 0.004029683999988265, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015329070000120737, "count": 10, "is_parallel": true, "self": 0.0015329070000120737 } } }, "UnityEnvironment.step": { "total": 0.03725122499997724, "count": 1, "is_parallel": true, "self": 0.0006500540000047295, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00041611000000330023, "count": 1, "is_parallel": true, "self": 0.00041611000000330023 }, "communicator.exchange": { "total": 0.0339988589999507, "count": 1, "is_parallel": true, "self": 0.0339988589999507 }, "steps_from_proto": { "total": 0.002186202000018511, "count": 1, "is_parallel": true, "self": 0.00041061500007799623, "children": { "_process_rank_one_or_two_observation": { "total": 0.001775586999940515, "count": 10, "is_parallel": true, "self": 0.001775586999940515 } } } } } } }, "UnityEnvironment.step": { "total": 256.33203057699416, "count": 18201, "is_parallel": true, "self": 11.179986439992831, "children": { "UnityEnvironment._generate_step_input": { "total": 5.820667991001187, "count": 18201, "is_parallel": true, "self": 5.820667991001187 }, "communicator.exchange": { "total": 202.21117861400802, "count": 18201, "is_parallel": true, "self": 202.21117861400802 }, "steps_from_proto": { "total": 37.12019753199212, "count": 18201, "is_parallel": true, "self": 7.149811906977618, "children": { "_process_rank_one_or_two_observation": { "total": 29.9703856250145, "count": 182010, "is_parallel": true, "self": 29.9703856250145 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0001171440000007351, "count": 1, "self": 0.0001171440000007351, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 487.97700585703285, "count": 512446, "is_parallel": true, "self": 11.293831761044771, "children": { "process_trajectory": { "total": 276.880678250988, "count": 512446, "is_parallel": true, "self": 276.3089507639879, "children": { "RLTrainer._checkpoint": { "total": 0.5717274870000892, "count": 4, "is_parallel": true, "self": 0.5717274870000892 } } }, "_update_policy": { "total": 199.80249584500007, "count": 90, "is_parallel": true, "self": 62.07358303399923, "children": { "TorchPPOOptimizer.update": { "total": 137.72891281100084, "count": 4587, "is_parallel": true, "self": 137.72891281100084 } } } } } } } } }, "TrainerController._save_models": { "total": 0.0881639220000352, "count": 1, "self": 0.0008461549999765339, "children": { "RLTrainer._checkpoint": { "total": 0.08731776700005867, "count": 1, "self": 0.08731776700005867 } } } } } } }