{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0131595134735107, "min": 1.0131595134735107, "max": 2.856973171234131, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9662.501953125, "min": 9662.501953125, "max": 29258.26171875, "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": 12.763596534729004, "min": 0.44558459520339966, "max": 12.763596534729004, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2488.9013671875, "min": 86.44341278076172, "max": 2573.105224609375, "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": 0.0759739646229861, "min": 0.06109209609964156, "max": 0.0759739646229861, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.3038958584919444, "min": 0.24436838439856623, "max": 0.35738778996450243, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.21341277235278897, "min": 0.12381837633324276, "max": 0.273795521142436, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8536510894111559, "min": 0.49527350533297104, "max": 1.3455667384699281, "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": 25.431818181818183, "min": 3.590909090909091, "max": 25.431818181818183, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1119.0, "min": 158.0, "max": 1386.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.431818181818183, "min": 3.590909090909091, "max": 25.431818181818183, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1119.0, "min": 158.0, "max": 1386.0, "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": "1707814791", "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": "2.2.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1707815263" }, "total": 471.49674966399994, "count": 1, "self": 0.43787338799995723, "children": { "run_training.setup": { "total": 0.08268079899994518, "count": 1, "self": 0.08268079899994518 }, "TrainerController.start_learning": { "total": 470.97619547700003, "count": 1, "self": 0.6198351989906996, "children": { "TrainerController._reset_env": { "total": 3.208210966000024, "count": 1, "self": 3.208210966000024 }, "TrainerController.advance": { "total": 467.05034504600917, "count": 18198, "self": 0.30502787900070416, "children": { "env_step": { "total": 466.74531716700847, "count": 18198, "self": 300.36149474501667, "children": { "SubprocessEnvManager._take_step": { "total": 166.0649330349986, "count": 18198, "self": 1.59725220301641, "children": { "TorchPolicy.evaluate": { "total": 164.4676808319822, "count": 18198, "self": 164.4676808319822 } } }, "workers": { "total": 0.3188893869931917, "count": 18198, "self": 0.0, "children": { "worker_root": { "total": 469.6561914229866, "count": 18198, "is_parallel": true, "self": 234.48015740300252, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004838591000066117, "count": 1, "is_parallel": true, "self": 0.003253668000184007, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015849229998821102, "count": 10, "is_parallel": true, "self": 0.0015849229998821102 } } }, "UnityEnvironment.step": { "total": 0.039050792000011825, "count": 1, "is_parallel": true, "self": 0.0006695449999369885, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00043630400000438385, "count": 1, "is_parallel": true, "self": 0.00043630400000438385 }, "communicator.exchange": { "total": 0.03585206900004323, "count": 1, "is_parallel": true, "self": 0.03585206900004323 }, "steps_from_proto": { "total": 0.002092874000027223, "count": 1, "is_parallel": true, "self": 0.00039885699993646995, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016940170000907528, "count": 10, "is_parallel": true, "self": 0.0016940170000907528 } } } } } } }, "UnityEnvironment.step": { "total": 235.17603401998406, "count": 18197, "is_parallel": true, "self": 11.176738809008611, "children": { "UnityEnvironment._generate_step_input": { "total": 5.901356077991181, "count": 18197, "is_parallel": true, "self": 5.901356077991181 }, "communicator.exchange": { "total": 181.36975037100297, "count": 18197, "is_parallel": true, "self": 181.36975037100297 }, "steps_from_proto": { "total": 36.7281887619813, "count": 18197, "is_parallel": true, "self": 6.966825156992286, "children": { "_process_rank_one_or_two_observation": { "total": 29.761363604989015, "count": 181970, "is_parallel": true, "self": 29.761363604989015 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0001266350000150851, "count": 1, "self": 0.0001266350000150851, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 461.09655034407467, "count": 728278, "is_parallel": true, "self": 16.257808646174794, "children": { "process_trajectory": { "total": 255.67517604190095, "count": 728278, "is_parallel": true, "self": 255.12825004590093, "children": { "RLTrainer._checkpoint": { "total": 0.5469259960000272, "count": 4, "is_parallel": true, "self": 0.5469259960000272 } } }, "_update_policy": { "total": 189.16356565599892, "count": 90, "is_parallel": true, "self": 52.65587269199318, "children": { "TorchPPOOptimizer.update": { "total": 136.50769296400574, "count": 4587, "is_parallel": true, "self": 136.50769296400574 } } } } } } } } }, "TrainerController._save_models": { "total": 0.09767763100012417, "count": 1, "self": 0.001101529000152368, "children": { "RLTrainer._checkpoint": { "total": 0.0965761019999718, "count": 1, "self": 0.0965761019999718 } } } } } } }