{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.3256784677505493, "min": 1.3256784677505493, "max": 2.4978251457214355, "count": 8 }, "SnowballTarget.Policy.Entropy.sum": { "value": 13722.09765625, "min": 7473.4931640625, "max": 23391.26171875, "count": 8 }, "SnowballTarget.Step.mean": { "value": 99960.0, "min": 29944.0, "max": 99960.0, "count": 8 }, "SnowballTarget.Step.sum": { "value": 99960.0, "min": 29944.0, "max": 99960.0, "count": 8 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 9.735746383666992, "min": 2.981156349182129, "max": 9.735746383666992, "count": 8 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 1986.09228515625, "min": 160.98243713378906, "max": 1986.09228515625, "count": 8 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 8 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 2189.0, "max": 10945.0, "count": 8 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06703904597191414, "min": 0.055809841973920506, "max": 0.076901034450195, "count": 8 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.3351952298595707, "min": 0.055809841973920506, "max": 0.38450517225097497, "count": 8 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.229793911763266, "min": 0.229793911763266, "max": 0.2871344493446397, "count": 8 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 1.14896955881633, "min": 0.24725254625082016, "max": 1.3874146216640286, "count": 8 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 0.000157176047608, "min": 0.000157176047608, "max": 0.00025617601460799997, "count": 8 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 0.00078588023804, "min": 0.00025617601460799997, "max": 0.00116538011154, "count": 8 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.152392, "min": 0.152392, "max": 0.185392, "count": 8 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.76196, "min": 0.185392, "max": 0.88846, "count": 8 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0026243608000000003, "min": 0.0026243608000000003, "max": 0.0042710608, "count": 8 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.013121804, "min": 0.0042710608, "max": 0.019434154, "count": 8 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 21.818181818181817, "min": 8.818181818181818, "max": 21.818181818181817, "count": 8 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1200.0, "min": 97.0, "max": 1200.0, "count": 8 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 21.818181818181817, "min": 8.818181818181818, "max": 21.818181818181817, "count": 8 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1200.0, "min": 97.0, "max": 1200.0, "count": 8 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 8 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 8 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1707073141", "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 --resume", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1707073310" }, "total": 169.00839194200012, "count": 1, "self": 0.005654195000033724, "children": { "run_training.setup": { "total": 0.046330031000024974, "count": 1, "self": 0.046330031000024974 }, "TrainerController.start_learning": { "total": 168.95640771600006, "count": 1, "self": 1.16319599098847, "children": { "TrainerController._reset_env": { "total": 2.032633347000001, "count": 1, "self": 2.032633347000001 }, "TrainerController.advance": { "total": 165.67177896601152, "count": 6798, "self": 0.10150164502215375, "children": { "env_step": { "total": 165.57027732098936, "count": 6798, "self": 106.36081562098116, "children": { "SubprocessEnvManager._take_step": { "total": 59.104578080007286, "count": 6798, "self": 0.5459434789966053, "children": { "TorchPolicy.evaluate": { "total": 58.55863460101068, "count": 6798, "self": 58.55863460101068 } } }, "workers": { "total": 0.10488362000091911, "count": 6797, "self": 0.0, "children": { "worker_root": { "total": 167.47266976998844, "count": 6797, "is_parallel": true, "self": 83.92561759099226, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0024009389999264386, "count": 1, "is_parallel": true, "self": 0.0006657589999576885, "children": { "_process_rank_one_or_two_observation": { "total": 0.00173517999996875, "count": 10, "is_parallel": true, "self": 0.00173517999996875 } } }, "UnityEnvironment.step": { "total": 0.03696543500018379, "count": 1, "is_parallel": true, "self": 0.0006904960000611027, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004026940000585455, "count": 1, "is_parallel": true, "self": 0.0004026940000585455 }, "communicator.exchange": { "total": 0.03376693199993497, "count": 1, "is_parallel": true, "self": 0.03376693199993497 }, "steps_from_proto": { "total": 0.002105313000129172, "count": 1, "is_parallel": true, "self": 0.00039066600015758013, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017146469999715919, "count": 10, "is_parallel": true, "self": 0.0017146469999715919 } } } } } } }, "UnityEnvironment.step": { "total": 83.54705217899618, "count": 6796, "is_parallel": true, "self": 3.9798186829823408, "children": { "UnityEnvironment._generate_step_input": { "total": 2.0643686680059545, "count": 6796, "is_parallel": true, "self": 2.0643686680059545 }, "communicator.exchange": { "total": 64.55227144500577, "count": 6796, "is_parallel": true, "self": 64.55227144500577 }, "steps_from_proto": { "total": 12.950593383002115, "count": 6796, "is_parallel": true, "self": 2.373907895006141, "children": { "_process_rank_one_or_two_observation": { "total": 10.576685487995974, "count": 67960, "is_parallel": true, "self": 10.576685487995974 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0007921210001313739, "count": 1, "self": 0.0007921210001313739, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 164.39003223298323, "count": 262604, "is_parallel": true, "self": 5.6990499909875325, "children": { "process_trajectory": { "total": 91.33518825799456, "count": 262604, "is_parallel": true, "self": 90.7733276689944, "children": { "RLTrainer._checkpoint": { "total": 0.5618605890001618, "count": 2, "is_parallel": true, "self": 0.5618605890001618 } } }, "_update_policy": { "total": 67.35579398400114, "count": 34, "is_parallel": true, "self": 18.783813645005466, "children": { "TorchPPOOptimizer.update": { "total": 48.57198033899567, "count": 1731, "is_parallel": true, "self": 48.57198033899567 } } } } } } } } }, "TrainerController._save_models": { "total": 0.08800729099993987, "count": 1, "self": 0.001211968000006891, "children": { "RLTrainer._checkpoint": { "total": 0.08679532299993298, "count": 1, "self": 0.08679532299993298 } } } } } } }