{ "name": "root", "gauges": { "PushBlock.Policy.Entropy.mean": { "value": 0.36918264627456665, "min": 0.36918264627456665, "max": 1.84763765335083, "count": 33 }, "PushBlock.Policy.Entropy.sum": { "value": 22221.841796875, "min": 22221.841796875, "max": 112099.875, "count": 33 }, "PushBlock.Step.mean": { "value": 1979989.0, "min": 59968.0, "max": 1979989.0, "count": 33 }, "PushBlock.Step.sum": { "value": 1979989.0, "min": 59968.0, "max": 1979989.0, "count": 33 }, "PushBlock.Policy.ExtrinsicValueEstimate.mean": { "value": 3.524479866027832, "min": -0.09835633635520935, "max": 3.524479866027832, "count": 33 }, "PushBlock.Policy.ExtrinsicValueEstimate.sum": { "value": 6065.6298828125, "min": -94.52043914794922, "max": 6065.6298828125, "count": 33 }, "PushBlock.Losses.PolicyLoss.mean": { "value": 0.06531524254004246, "min": 0.06531524254004246, "max": 0.07230422536205226, "count": 33 }, "PushBlock.Losses.PolicyLoss.sum": { "value": 1.8941420336612316, "min": 0.9877540243655976, "max": 2.0708480319105242, "count": 33 }, "PushBlock.Losses.ValueLoss.mean": { "value": 0.3559052664226147, "min": 1.0239713772145584e-05, "max": 0.41948080000778043, "count": 33 }, "PushBlock.Losses.ValueLoss.sum": { "value": 10.321252726255826, "min": 0.00015359570658218376, "max": 12.164943200225633, "count": 33 }, "PushBlock.Policy.LearningRate.mean": { "value": 7.590966435227584e-06, "min": 7.590966435227584e-06, "max": 0.00029544960151679995, "count": 33 }, "PushBlock.Policy.LearningRate.sum": { "value": 0.00022013802662159996, "min": 0.00022013802662159996, "max": 0.0070045391651538, "count": 33 }, "PushBlock.Policy.Epsilon.mean": { "value": 0.10253028965517243, "min": 0.10253028965517243, "max": 0.1984832, "count": 33 }, "PushBlock.Policy.Epsilon.sum": { "value": 2.9733784000000005, "min": 2.7787648, "max": 5.2348462, "count": 33 }, "PushBlock.Policy.Beta.mean": { "value": 0.0002627759365517241, "min": 0.0002627759365517241, "max": 0.00984847168, "count": 33 }, "PushBlock.Policy.Beta.sum": { "value": 0.00762050216, "min": 0.00762050216, "max": 0.23354113538, "count": 33 }, "PushBlock.Environment.EpisodeLength.mean": { "value": 45.92818110850898, "min": 45.92818110850898, "max": 999.0, "count": 33 }, "PushBlock.Environment.EpisodeLength.sum": { "value": 58834.0, "min": 31968.0, "max": 64324.0, "count": 33 }, "PushBlock.Environment.CumulativeReward.mean": { "value": 4.891086941858094, "min": -1.0000000447034836, "max": 4.902474769966761, "count": 33 }, "PushBlock.Environment.CumulativeReward.sum": { "value": 6270.373459462076, "min": -64.00000286102295, "max": 6270.373459462076, "count": 33 }, "PushBlock.Policy.ExtrinsicReward.mean": { "value": 4.891086941858094, "min": -1.0000000447034836, "max": 4.902474769966761, "count": 33 }, "PushBlock.Policy.ExtrinsicReward.sum": { "value": 6270.373459462076, "min": -64.00000286102295, "max": 6270.373459462076, "count": 33 }, "PushBlock.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 33 }, "PushBlock.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 33 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1661028747", "python_version": "3.9.7 | packaged by conda-forge | (default, Sep 29 2021, 19:23:11) \n[GCC 9.4.0]", "command_line_arguments": "/home/studio-lab-user/.conda/envs/d2l/bin/mlagents-learn ./config/ppo/PushBlock.yaml --env=./trained-envs-executables/linux/PushBlock/PushBlock --run-id=PushBlock Training --no-graphics", "mlagents_version": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.21.4", "end_time_seconds": "1661030447" }, "total": 1700.625083998, "count": 1, "self": 0.27019369400022697, "children": { "run_training.setup": { "total": 0.07572018399991975, "count": 1, "self": 0.07572018399991975 }, "TrainerController.start_learning": { "total": 1700.27917012, "count": 1, "self": 1.593551067011731, "children": { "TrainerController._reset_env": { "total": 12.003173340999865, "count": 1, "self": 12.003173340999865 }, "TrainerController.advance": { "total": 1686.6228198569884, "count": 75568, "self": 1.4462087121214608, "children": { "env_step": { "total": 971.9844109099299, "count": 75568, "self": 877.8616919780079, "children": { "SubprocessEnvManager._take_step": { "total": 93.2743697950034, "count": 75568, "self": 4.636906597020243, "children": { "TorchPolicy.evaluate": { "total": 88.63746319798315, "count": 62528, "self": 28.58412011988935, "children": { "TorchPolicy.sample_actions": { "total": 60.0533430780938, "count": 62528, "self": 60.0533430780938 } } } } }, "workers": { "total": 0.848349136918614, "count": 75568, "self": 0.0, "children": { "worker_root": { "total": 1697.377955602092, "count": 75568, "is_parallel": true, "self": 939.1471152440615, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.003576241000018854, "count": 1, "is_parallel": true, "self": 0.0016262459998870327, "children": { "_process_rank_one_or_two_observation": { "total": 0.0019499950001318211, "count": 4, "is_parallel": true, "self": 0.0019499950001318211 } } }, "UnityEnvironment.step": { "total": 0.02470750600014071, "count": 1, "is_parallel": true, "self": 0.0008270579999134497, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00043646000017361075, "count": 1, "is_parallel": true, "self": 0.00043646000017361075 }, "communicator.exchange": { "total": 0.020933761000151208, "count": 1, "is_parallel": true, "self": 0.020933761000151208 }, "steps_from_proto": { "total": 0.002510226999902443, "count": 1, "is_parallel": true, "self": 0.0004533799999535404, "children": { "_process_rank_one_or_two_observation": { "total": 0.0020568469999489025, "count": 4, "is_parallel": true, "self": 0.0020568469999489025 } } } } } } }, "UnityEnvironment.step": { "total": 758.2308403580305, "count": 75567, "is_parallel": true, "self": 33.301698001971545, "children": { "UnityEnvironment._generate_step_input": { "total": 26.422092879958655, "count": 75567, "is_parallel": true, "self": 26.422092879958655 }, "communicator.exchange": { "total": 604.322116844068, "count": 75567, "is_parallel": true, "self": 604.322116844068 }, "steps_from_proto": { "total": 94.18493263203231, "count": 75567, "is_parallel": true, "self": 18.92606160921855, "children": { "_process_rank_one_or_two_observation": { "total": 75.25887102281376, "count": 302268, "is_parallel": true, "self": 75.25887102281376 } } } } } } } } } } }, "trainer_advance": { "total": 713.192200234937, "count": 75568, "self": 3.11769389285314, "children": { "process_trajectory": { "total": 179.35090118809308, "count": 75568, "self": 179.05766282609375, "children": { "RLTrainer._checkpoint": { "total": 0.29323836199932884, "count": 4, "self": 0.29323836199932884 } } }, "_update_policy": { "total": 530.7236051539908, "count": 888, "self": 281.29957376098946, "children": { "TorchPPOOptimizer.update": { "total": 249.42403139300131, "count": 46191, "self": 249.42403139300131 } } } } } } }, "trainer_threads": { "total": 1.1100000847363845e-06, "count": 1, "self": 1.1100000847363845e-06 }, "TrainerController._save_models": { "total": 0.059624744999837276, "count": 1, "self": 0.00044027100011589937, "children": { "RLTrainer._checkpoint": { "total": 0.059184473999721376, "count": 1, "self": 0.059184473999721376 } } } } } } }