{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.407550573348999, "min": 1.407550573348999, "max": 1.428611159324646, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 71488.0859375, "min": 69080.6953125, "max": 77182.703125, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 83.66440677966102, "min": 78.64193548387097, "max": 387.0077519379845, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49362.0, "min": 48739.0, "max": 50073.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999926.0, "min": 49303.0, "max": 1999926.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999926.0, "min": 49303.0, "max": 1999926.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.4860761165618896, "min": 0.1523505002260208, "max": 2.513928174972534, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1466.784912109375, "min": 19.500864028930664, "max": 1532.2078857421875, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.896628303952136, "min": 1.7316654763417318, "max": 4.078883149545558, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2299.0106993317604, "min": 221.65318097174168, "max": 2392.5368205308914, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.896628303952136, "min": 1.7316654763417318, "max": 4.078883149545558, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2299.0106993317604, "min": 221.65318097174168, "max": 2392.5368205308914, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.01717438139215422, "min": 0.012967907763656208, "max": 0.02018370325887291, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.051523144176462664, "min": 0.025935815527312417, "max": 0.06055110977661873, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.06302236210968759, "min": 0.021789403259754182, "max": 0.06302236210968759, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.18906708632906277, "min": 0.043578806519508365, "max": 0.18906708632906277, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.4444988518666697e-06, "min": 3.4444988518666697e-06, "max": 0.000295286326571225, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0333496555600009e-05, "min": 1.0333496555600009e-05, "max": 0.0008441161686279502, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10114813333333335, "min": 0.10114813333333335, "max": 0.198428775, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30344440000000006, "min": 0.20747689999999996, "max": 0.58137205, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.72918533333334e-05, "min": 6.72918533333334e-05, "max": 0.0049215958725, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00020187556000000022, "min": 0.00020187556000000022, "max": 0.014070465295000001, "count": 40 }, "Huggy.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 }, "Huggy.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1693000607", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy --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": "1693003258" }, "total": 2650.887270763, "count": 1, "self": 0.4486288679995596, "children": { "run_training.setup": { "total": 0.04171390800001973, "count": 1, "self": 0.04171390800001973 }, "TrainerController.start_learning": { "total": 2650.3969279870003, "count": 1, "self": 4.81166919614725, "children": { "TrainerController._reset_env": { "total": 5.286762990999932, "count": 1, "self": 5.286762990999932 }, "TrainerController.advance": { "total": 2640.1571647488536, "count": 233098, "self": 4.991912429822605, "children": { "env_step": { "total": 2044.5265322231064, "count": 233098, "self": 1722.6456540281843, "children": { "SubprocessEnvManager._take_step": { "total": 318.60366948099704, "count": 233098, "self": 17.832372236092397, "children": { "TorchPolicy.evaluate": { "total": 300.77129724490464, "count": 223037, "self": 300.77129724490464 } } }, "workers": { "total": 3.27720871392512, "count": 233098, "self": 0.0, "children": { "worker_root": { "total": 2642.3072844929566, "count": 233098, "is_parallel": true, "self": 1240.4021526860051, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0009562459999870043, "count": 1, "is_parallel": true, "self": 0.0002876370000421957, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006686089999448086, "count": 2, "is_parallel": true, "self": 0.0006686089999448086 } } }, "UnityEnvironment.step": { "total": 0.05294102999994266, "count": 1, "is_parallel": true, "self": 0.000372372999891013, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002549629999748504, "count": 1, "is_parallel": true, "self": 0.0002549629999748504 }, "communicator.exchange": { "total": 0.05147999200005415, "count": 1, "is_parallel": true, "self": 0.05147999200005415 }, "steps_from_proto": { "total": 0.0008337020000226403, "count": 1, "is_parallel": true, "self": 0.000263334000010218, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005703680000124223, "count": 2, "is_parallel": true, "self": 0.0005703680000124223 } } } } } } }, "UnityEnvironment.step": { "total": 1401.9051318069514, "count": 233097, "is_parallel": true, "self": 41.387151856047694, "children": { "UnityEnvironment._generate_step_input": { "total": 87.67197050301831, "count": 233097, "is_parallel": true, "self": 87.67197050301831 }, "communicator.exchange": { "total": 1169.3524227879007, "count": 233097, "is_parallel": true, "self": 1169.3524227879007 }, "steps_from_proto": { "total": 103.49358665998477, "count": 233097, "is_parallel": true, "self": 39.25497721108434, "children": { "_process_rank_one_or_two_observation": { "total": 64.23860944890043, "count": 466194, "is_parallel": true, "self": 64.23860944890043 } } } } } } } } } } }, "trainer_advance": { "total": 590.6387200959247, "count": 233098, "self": 7.217933865059422, "children": { "process_trajectory": { "total": 159.58540925486466, "count": 233098, "self": 157.86416886686413, "children": { "RLTrainer._checkpoint": { "total": 1.721240388000524, "count": 10, "self": 1.721240388000524 } } }, "_update_policy": { "total": 423.8353769760006, "count": 97, "self": 361.65712315700773, "children": { "TorchPPOOptimizer.update": { "total": 62.17825381899286, "count": 2910, "self": 62.17825381899286 } } } } } } }, "trainer_threads": { "total": 1.1100000847363845e-06, "count": 1, "self": 1.1100000847363845e-06 }, "TrainerController._save_models": { "total": 0.1413299409996398, "count": 1, "self": 0.0024211369996010035, "children": { "RLTrainer._checkpoint": { "total": 0.1389088040000388, "count": 1, "self": 0.1389088040000388 } } } } } } }