{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9169906377792358, "min": 0.9168095588684082, "max": 2.8741257190704346, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8815.9482421875, "min": 8815.9482421875, "max": 29433.921875, "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": 12.716064453125, "min": 0.12716500461101532, "max": 12.716064453125, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2479.632568359375, "min": 24.67000961303711, "max": 2563.40625, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06567128748928572, "min": 0.05996350110117597, "max": 0.07386797968270806, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.26268514995714287, "min": 0.2398540044047039, "max": 0.36933989841354026, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19011369238004963, "min": 0.10754778650109931, "max": 0.2790243513151711, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7604547695201985, "min": 0.43019114600439723, "max": 1.344088671838536, "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": 25.295454545454547, "min": 3.1136363636363638, "max": 25.295454545454547, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1113.0, "min": 137.0, "max": 1380.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.295454545454547, "min": 3.1136363636363638, "max": 25.295454545454547, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1113.0, "min": 137.0, "max": 1380.0, "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": "1704450084", "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", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.2+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1704450548" }, "total": 463.78588035199994, "count": 1, "self": 0.7953592649998882, "children": { "run_training.setup": { "total": 0.05539418699993348, "count": 1, "self": 0.05539418699993348 }, "TrainerController.start_learning": { "total": 462.9351269000001, "count": 1, "self": 0.6069211579889497, "children": { "TrainerController._reset_env": { "total": 3.572563425999988, "count": 1, "self": 3.572563425999988 }, "TrainerController.advance": { "total": 458.6234850180109, "count": 18220, "self": 0.2975554900157249, "children": { "env_step": { "total": 458.3259295279952, "count": 18220, "self": 302.9185383160009, "children": { "SubprocessEnvManager._take_step": { "total": 155.107288337995, "count": 18220, "self": 1.5242089099914438, "children": { "TorchPolicy.evaluate": { "total": 153.58307942800354, "count": 18220, "self": 153.58307942800354 } } }, "workers": { "total": 0.3001028739993217, "count": 18220, "self": 0.0, "children": { "worker_root": { "total": 461.51556401000744, "count": 18220, "is_parallel": true, "self": 226.3698143999943, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004796544999976504, "count": 1, "is_parallel": true, "self": 0.0031014989997402154, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016950460002362888, "count": 10, "is_parallel": true, "self": 0.0016950460002362888 } } }, "UnityEnvironment.step": { "total": 0.04527150499995969, "count": 1, "is_parallel": true, "self": 0.0006935549998843271, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00045606000003317604, "count": 1, "is_parallel": true, "self": 0.00045606000003317604 }, "communicator.exchange": { "total": 0.04202243000008821, "count": 1, "is_parallel": true, "self": 0.04202243000008821 }, "steps_from_proto": { "total": 0.0020994599999539787, "count": 1, "is_parallel": true, "self": 0.00039424800002052507, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017052119999334536, "count": 10, "is_parallel": true, "self": 0.0017052119999334536 } } } } } } }, "UnityEnvironment.step": { "total": 235.14574961001313, "count": 18219, "is_parallel": true, "self": 11.066490466999426, "children": { "UnityEnvironment._generate_step_input": { "total": 5.681041889004973, "count": 18219, "is_parallel": true, "self": 5.681041889004973 }, "communicator.exchange": { "total": 182.70101114700617, "count": 18219, "is_parallel": true, "self": 182.70101114700617 }, "steps_from_proto": { "total": 35.69720610700256, "count": 18219, "is_parallel": true, "self": 6.747745324992366, "children": { "_process_rank_one_or_two_observation": { "total": 28.949460782010192, "count": 182190, "is_parallel": true, "self": 28.949460782010192 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00017983100019591802, "count": 1, "self": 0.00017983100019591802, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 452.81469721800863, "count": 694621, "is_parallel": true, "self": 14.66126733196927, "children": { "process_trajectory": { "total": 250.40456455103856, "count": 694621, "is_parallel": true, "self": 249.3397353170385, "children": { "RLTrainer._checkpoint": { "total": 1.064829234000058, "count": 4, "is_parallel": true, "self": 1.064829234000058 } } }, "_update_policy": { "total": 187.7488653350008, "count": 90, "is_parallel": true, "self": 58.34706841200443, "children": { "TorchPPOOptimizer.update": { "total": 129.40179692299637, "count": 4587, "is_parallel": true, "self": 129.40179692299637 } } } } } } } } }, "TrainerController._save_models": { "total": 0.13197746700006974, "count": 1, "self": 0.0013683120000678173, "children": { "RLTrainer._checkpoint": { "total": 0.13060915500000192, "count": 1, "self": 0.13060915500000192 } } } } } } }