{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.789790689945221, "min": 0.789790689945221, "max": 2.8516151905059814, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7532.23388671875, "min": 7532.23388671875, "max": 29234.7578125, "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": 12.553600311279297, "min": 0.31576886773109436, "max": 12.565973281860352, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2447.9521484375, "min": 61.259159088134766, "max": 2559.8203125, "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": 0.06633490494734325, "min": 0.05883006659760391, "max": 0.07328271560978536, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.265339619789373, "min": 0.23532026639041564, "max": 0.3541172459606291, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.2226457012196382, "min": 0.10835672097677804, "max": 0.29302526477213, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8905828048785528, "min": 0.43342688390711215, "max": 1.4457648639001097, "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": 24.431818181818183, "min": 3.2045454545454546, "max": 24.954545454545453, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1075.0, "min": 141.0, "max": 1354.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.431818181818183, "min": 3.2045454545454546, "max": 24.954545454545453, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1075.0, "min": 141.0, "max": 1354.0, "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": "1678708943", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[GCC 9.4.0]", "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": "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": "1678709447" }, "total": 503.5343705660001, "count": 1, "self": 0.4466016110002329, "children": { "run_training.setup": { "total": 0.10529778699992676, "count": 1, "self": 0.10529778699992676 }, "TrainerController.start_learning": { "total": 502.98247116799996, "count": 1, "self": 0.6605594869967035, "children": { "TrainerController._reset_env": { "total": 9.693524621999927, "count": 1, "self": 9.693524621999927 }, "TrainerController.advance": { "total": 492.4855847980033, "count": 18201, "self": 0.3377977729927579, "children": { "env_step": { "total": 492.14778702501053, "count": 18201, "self": 355.63209381803574, "children": { "SubprocessEnvManager._take_step": { "total": 136.0126664359792, "count": 18201, "self": 2.2921918159628376, "children": { "TorchPolicy.evaluate": { "total": 133.72047462001638, "count": 18201, "self": 133.72047462001638 } } }, "workers": { "total": 0.5030267709955751, "count": 18201, "self": 0.0, "children": { "worker_root": { "total": 501.31981936898444, "count": 18201, "is_parallel": true, "self": 237.22169087699592, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006739766000009695, "count": 1, "is_parallel": true, "self": 0.0047242389997563805, "children": { "_process_rank_one_or_two_observation": { "total": 0.0020155270002533143, "count": 10, "is_parallel": true, "self": 0.0020155270002533143 } } }, "UnityEnvironment.step": { "total": 0.06989678499996899, "count": 1, "is_parallel": true, "self": 0.0006936530000984931, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00036460799992710236, "count": 1, "is_parallel": true, "self": 0.00036460799992710236 }, "communicator.exchange": { "total": 0.06640127899993331, "count": 1, "is_parallel": true, "self": 0.06640127899993331 }, "steps_from_proto": { "total": 0.00243724500001008, "count": 1, "is_parallel": true, "self": 0.00041529100019488396, "children": { "_process_rank_one_or_two_observation": { "total": 0.002021953999815196, "count": 10, "is_parallel": true, "self": 0.002021953999815196 } } } } } } }, "UnityEnvironment.step": { "total": 264.0981284919885, "count": 18200, "is_parallel": true, "self": 10.351048845991158, "children": { "UnityEnvironment._generate_step_input": { "total": 5.706464272997891, "count": 18200, "is_parallel": true, "self": 5.706464272997891 }, "communicator.exchange": { "total": 213.10450206699602, "count": 18200, "is_parallel": true, "self": 213.10450206699602 }, "steps_from_proto": { "total": 34.93611330600345, "count": 18200, "is_parallel": true, "self": 7.144953224954634, "children": { "_process_rank_one_or_two_observation": { "total": 27.791160081048815, "count": 182000, "is_parallel": true, "self": 27.791160081048815 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00023254300003827666, "count": 1, "self": 0.00023254300003827666, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 488.6465625500176, "count": 441939, "is_parallel": true, "self": 11.159618020983999, "children": { "process_trajectory": { "total": 272.9937724030351, "count": 441939, "is_parallel": true, "self": 272.0877884310353, "children": { "RLTrainer._checkpoint": { "total": 0.9059839719998308, "count": 4, "is_parallel": true, "self": 0.9059839719998308 } } }, "_update_policy": { "total": 204.4931721259985, "count": 90, "is_parallel": true, "self": 73.27936789900252, "children": { "TorchPPOOptimizer.update": { "total": 131.213804226996, "count": 4587, "is_parallel": true, "self": 131.213804226996 } } } } } } } } }, "TrainerController._save_models": { "total": 0.1425697180000043, "count": 1, "self": 0.001183841999818469, "children": { "RLTrainer._checkpoint": { "total": 0.14138587600018582, "count": 1, "self": 0.14138587600018582 } } } } } } }