{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4088757038116455, "min": 1.4088757038116455, "max": 1.429335117340088, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70245.1328125, "min": 69292.9375, "max": 77248.9921875, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 101.43032786885246, "min": 88.1032028469751, "max": 405.869918699187, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49498.0, "min": 48818.0, "max": 50152.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999951.0, "min": 49591.0, "max": 1999951.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999951.0, "min": 49591.0, "max": 1999951.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.3906569480895996, "min": 0.05552562326192856, "max": 2.428147315979004, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1166.640625, "min": 6.774126052856445, "max": 1321.307373046875, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.757790986753878, "min": 1.8421961704238516, "max": 3.9528469250580973, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1833.8020015358925, "min": 224.7479327917099, "max": 2123.33960211277, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.757790986753878, "min": 1.8421961704238516, "max": 3.9528469250580973, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1833.8020015358925, "min": 224.7479327917099, "max": 2123.33960211277, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.017162580473167408, "min": 0.013502292323209986, "max": 0.019740026009579498, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.05148774141950223, "min": 0.02700458464641997, "max": 0.05922007802873849, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.04829215643306573, "min": 0.02251113612825672, "max": 0.057037567533552644, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.1448764692991972, "min": 0.04502227225651344, "max": 0.16508131908873716, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.21569892813334e-06, "min": 3.21569892813334e-06, "max": 0.000295312426562525, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 9.64709678440002e-06, "min": 9.64709678440002e-06, "max": 0.0008440194186601997, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10107186666666668, "min": 0.10107186666666668, "max": 0.198437475, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30321560000000003, "min": 0.2073986000000001, "max": 0.5813398000000001, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.34861466666668e-05, "min": 6.34861466666668e-05, "max": 0.004922030002499999, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00019045844000000042, "min": 0.00019045844000000042, "max": 0.01406885602, "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": "1729029449", "python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [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=Huggy2 --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.4.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1729032162" }, "total": 2713.366583278, "count": 1, "self": 0.4459521279995897, "children": { "run_training.setup": { "total": 0.05650099800004682, "count": 1, "self": 0.05650099800004682 }, "TrainerController.start_learning": { "total": 2712.864130152, "count": 1, "self": 5.317868167071538, "children": { "TrainerController._reset_env": { "total": 4.801325205000012, "count": 1, "self": 4.801325205000012 }, "TrainerController.advance": { "total": 2702.6241080079285, "count": 231949, "self": 5.308026914898619, "children": { "env_step": { "total": 2186.212354598971, "count": 231949, "self": 1721.4082549848204, "children": { "SubprocessEnvManager._take_step": { "total": 461.43416606604023, "count": 231949, "self": 17.981248432945563, "children": { "TorchPolicy.evaluate": { "total": 443.45291763309467, "count": 222974, "self": 443.45291763309467 } } }, "workers": { "total": 3.3699335481104526, "count": 231949, "self": 0.0, "children": { "worker_root": { "total": 2704.8190463880196, "count": 231949, "is_parallel": true, "self": 1320.0870276349608, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0009013049999566647, "count": 1, "is_parallel": true, "self": 0.0002701089998708994, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006311960000857653, "count": 2, "is_parallel": true, "self": 0.0006311960000857653 } } }, "UnityEnvironment.step": { "total": 0.04675411999994594, "count": 1, "is_parallel": true, "self": 0.00042271599977539154, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002021720000584537, "count": 1, "is_parallel": true, "self": 0.0002021720000584537 }, "communicator.exchange": { "total": 0.045369152000034774, "count": 1, "is_parallel": true, "self": 0.045369152000034774 }, "steps_from_proto": { "total": 0.0007600800000773233, "count": 1, "is_parallel": true, "self": 0.00020628800018585025, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005537919998914731, "count": 2, "is_parallel": true, "self": 0.0005537919998914731 } } } } } } }, "UnityEnvironment.step": { "total": 1384.7320187530588, "count": 231948, "is_parallel": true, "self": 40.977991624257356, "children": { "UnityEnvironment._generate_step_input": { "total": 88.15179943701969, "count": 231948, "is_parallel": true, "self": 88.15179943701969 }, "communicator.exchange": { "total": 1156.9890603727981, "count": 231948, "is_parallel": true, "self": 1156.9890603727981 }, "steps_from_proto": { "total": 98.61316731898364, "count": 231948, "is_parallel": true, "self": 37.358022560023414, "children": { "_process_rank_one_or_two_observation": { "total": 61.25514475896023, "count": 463896, "is_parallel": true, "self": 61.25514475896023 } } } } } } } } } } }, "trainer_advance": { "total": 511.10372649405883, "count": 231949, "self": 8.1870296110435, "children": { "process_trajectory": { "total": 172.39551782001615, "count": 231949, "self": 170.94282985901611, "children": { "RLTrainer._checkpoint": { "total": 1.4526879610000378, "count": 10, "self": 1.4526879610000378 } } }, "_update_policy": { "total": 330.5211790629992, "count": 97, "self": 263.75173008100353, "children": { "TorchPPOOptimizer.update": { "total": 66.76944898199565, "count": 2910, "self": 66.76944898199565 } } } } } } }, "trainer_threads": { "total": 1.7160000425064936e-06, "count": 1, "self": 1.7160000425064936e-06 }, "TrainerController._save_models": { "total": 0.12082705600005283, "count": 1, "self": 0.0020421110002644127, "children": { "RLTrainer._checkpoint": { "total": 0.11878494499978842, "count": 1, "self": 0.11878494499978842 } } } } } } }