{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9439092874526978, "min": 0.9439092874526978, "max": 2.8577966690063477, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9033.2119140625, "min": 9033.2119140625, "max": 29329.56640625, "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": 12.824914932250977, "min": 0.3604266345500946, "max": 12.824914932250977, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2500.8583984375, "min": 69.92276763916016, "max": 2594.408447265625, "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": 0.06835880223090998, "min": 0.059975697444500764, "max": 0.07332421091451383, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2734352089236399, "min": 0.2555790173366903, "max": 0.3666210545725691, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.18885370007916993, "min": 0.11159278717184185, "max": 0.2889607545791888, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7554148003166797, "min": 0.4463711486873674, "max": 1.444803772895944, "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": 25.545454545454547, "min": 3.1818181818181817, "max": 25.545454545454547, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1124.0, "min": 140.0, "max": 1390.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.545454545454547, "min": 3.1818181818181817, "max": 25.545454545454547, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1124.0, "min": 140.0, "max": 1390.0, "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": "1691542293", "python_version": "3.9.17 (main, Jul 5 2023, 21:05:34) \n[GCC 11.2.0]", "command_line_arguments": "/home/renatostrianese/anaconda3/envs/RenatoTF/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1691542657" }, "total": 364.68023378199996, "count": 1, "self": 0.2699723219993757, "children": { "run_training.setup": { "total": 0.030781919000219204, "count": 1, "self": 0.030781919000219204 }, "TrainerController.start_learning": { "total": 364.37947954100036, "count": 1, "self": 0.4919213199891601, "children": { "TrainerController._reset_env": { "total": 3.991919869999947, "count": 1, "self": 3.991919869999947 }, "TrainerController.advance": { "total": 359.7802025300107, "count": 18205, "self": 0.23165687700748094, "children": { "env_step": { "total": 359.5485456530032, "count": 18205, "self": 269.6388230039711, "children": { "SubprocessEnvManager._take_step": { "total": 89.65193954601182, "count": 18205, "self": 1.2264293549997092, "children": { "TorchPolicy.evaluate": { "total": 88.42551019101211, "count": 18205, "self": 88.42551019101211 } } }, "workers": { "total": 0.2577831030203015, "count": 18205, "self": 0.0, "children": { "worker_root": { "total": 363.67353635802556, "count": 18205, "is_parallel": true, "self": 169.9355333179974, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004622735999873839, "count": 1, "is_parallel": true, "self": 0.0008889169994290569, "children": { "_process_rank_one_or_two_observation": { "total": 0.0037338190004447824, "count": 10, "is_parallel": true, "self": 0.0037338190004447824 } } }, "UnityEnvironment.step": { "total": 0.02387658600036957, "count": 1, "is_parallel": true, "self": 0.00030577599954995094, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005015260003347066, "count": 1, "is_parallel": true, "self": 0.0005015260003347066 }, "communicator.exchange": { "total": 0.0219661740002266, "count": 1, "is_parallel": true, "self": 0.0219661740002266 }, "steps_from_proto": { "total": 0.0011031100002583116, "count": 1, "is_parallel": true, "self": 0.00024352499804081162, "children": { "_process_rank_one_or_two_observation": { "total": 0.0008595850022175, "count": 10, "is_parallel": true, "self": 0.0008595850022175 } } } } } } }, "UnityEnvironment.step": { "total": 193.73800304002816, "count": 18204, "is_parallel": true, "self": 9.894272852064205, "children": { "UnityEnvironment._generate_step_input": { "total": 4.646378561956226, "count": 18204, "is_parallel": true, "self": 4.646378561956226 }, "communicator.exchange": { "total": 151.0854734339846, "count": 18204, "is_parallel": true, "self": 151.0854734339846 }, "steps_from_proto": { "total": 28.11187819202314, "count": 18204, "is_parallel": true, "self": 5.17304135415452, "children": { "_process_rank_one_or_two_observation": { "total": 22.93883683786862, "count": 182040, "is_parallel": true, "self": 22.93883683786862 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00011856400033138925, "count": 1, "self": 0.00011856400033138925, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 358.7516835789738, "count": 211926, "is_parallel": true, "self": 3.577767863358531, "children": { "process_trajectory": { "total": 205.3458995376095, "count": 211926, "is_parallel": true, "self": 204.60487416860906, "children": { "RLTrainer._checkpoint": { "total": 0.7410253690004538, "count": 4, "is_parallel": true, "self": 0.7410253690004538 } } }, "_update_policy": { "total": 149.82801617800578, "count": 90, "is_parallel": true, "self": 37.9139420719448, "children": { "TorchPPOOptimizer.update": { "total": 111.91407410606098, "count": 4587, "is_parallel": true, "self": 111.91407410606098 } } } } } } } } }, "TrainerController._save_models": { "total": 0.11531725700024253, "count": 1, "self": 0.0007198670009529451, "children": { "RLTrainer._checkpoint": { "total": 0.11459738999928959, "count": 1, "self": 0.11459738999928959 } } } } } } }