{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4053677320480347, "min": 1.4053677320480347, "max": 1.4259312152862549, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 71153.765625, "min": 69050.25, "max": 77134.546875, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 69.74257425742574, "min": 67.86501377410468, "max": 389.06201550387595, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49308.0, "min": 49146.0, "max": 50189.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999963.0, "min": 49790.0, "max": 1999963.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999963.0, "min": 49790.0, "max": 1999963.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.500272035598755, "min": 0.11183132231235504, "max": 2.5504305362701416, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1767.6922607421875, "min": 14.314409255981445, "max": 1804.9974365234375, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 4.015621589130526, "min": 1.7363192656775936, "max": 4.119485528465564, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2839.0444635152817, "min": 222.248866006732, "max": 2859.466530919075, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 4.015621589130526, "min": 1.7363192656775936, "max": 4.119485528465564, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2839.0444635152817, "min": 222.248866006732, "max": 2859.466530919075, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.016372030006217148, "min": 0.012775441022555848, "max": 0.02017860772126975, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.04911609001865144, "min": 0.025550882045111696, "max": 0.060535823163809246, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05755272313124604, "min": 0.022136131239434084, "max": 0.06408473365008832, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.17265816939373813, "min": 0.04427226247886817, "max": 0.18181039119760195, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 4.026298657933336e-06, "min": 4.026298657933336e-06, "max": 0.0002953056015647999, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.2078895973800007e-05, "min": 1.2078895973800007e-05, "max": 0.0008439582186805999, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10134206666666669, "min": 0.10134206666666669, "max": 0.19843520000000003, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.3040262000000001, "min": 0.20781370000000002, "max": 0.5813193999999999, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.69691266666667e-05, "min": 7.69691266666667e-05, "max": 0.00492191648, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.0002309073800000001, "min": 0.0002309073800000001, "max": 0.014067838060000002, "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": "1710969667", "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/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy2 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1710972101" }, "total": 2433.127564386, "count": 1, "self": 0.4449004379998769, "children": { "run_training.setup": { "total": 0.055602150000026995, "count": 1, "self": 0.055602150000026995 }, "TrainerController.start_learning": { "total": 2432.627061798, "count": 1, "self": 4.4082539599880874, "children": { "TrainerController._reset_env": { "total": 2.8471103440000434, "count": 1, "self": 2.8471103440000434 }, "TrainerController.advance": { "total": 2425.259057522012, "count": 233973, "self": 4.6306835810601115, "children": { "env_step": { "total": 1946.9654672889258, "count": 233973, "self": 1613.6466259309009, "children": { "SubprocessEnvManager._take_step": { "total": 330.3655579790759, "count": 233973, "self": 17.14362174899179, "children": { "TorchPolicy.evaluate": { "total": 313.2219362300841, "count": 222961, "self": 313.2219362300841 } } }, "workers": { "total": 2.9532833789488677, "count": 233973, "self": 0.0, "children": { "worker_root": { "total": 2425.235101579092, "count": 233973, "is_parallel": true, "self": 1123.5905624321817, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.000954729000000043, "count": 1, "is_parallel": true, "self": 0.000233162999961678, "children": { "_process_rank_one_or_two_observation": { "total": 0.000721566000038365, "count": 2, "is_parallel": true, "self": 0.000721566000038365 } } }, "UnityEnvironment.step": { "total": 0.029097812999907546, "count": 1, "is_parallel": true, "self": 0.00037801799987846607, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000206791999971756, "count": 1, "is_parallel": true, "self": 0.000206791999971756 }, "communicator.exchange": { "total": 0.027737515000012536, "count": 1, "is_parallel": true, "self": 0.027737515000012536 }, "steps_from_proto": { "total": 0.0007754880000447884, "count": 1, "is_parallel": true, "self": 0.00021229399999356247, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005631940000512259, "count": 2, "is_parallel": true, "self": 0.0005631940000512259 } } } } } } }, "UnityEnvironment.step": { "total": 1301.6445391469101, "count": 233972, "is_parallel": true, "self": 39.82749181896315, "children": { "UnityEnvironment._generate_step_input": { "total": 84.81793866495559, "count": 233972, "is_parallel": true, "self": 84.81793866495559 }, "communicator.exchange": { "total": 1082.466474179997, "count": 233972, "is_parallel": true, "self": 1082.466474179997 }, "steps_from_proto": { "total": 94.53263448299447, "count": 233972, "is_parallel": true, "self": 35.36797142484318, "children": { "_process_rank_one_or_two_observation": { "total": 59.16466305815129, "count": 467944, "is_parallel": true, "self": 59.16466305815129 } } } } } } } } } } }, "trainer_advance": { "total": 473.6629066520262, "count": 233973, "self": 6.804605148945711, "children": { "process_trajectory": { "total": 164.2726389700798, "count": 233973, "self": 162.98955898307906, "children": { "RLTrainer._checkpoint": { "total": 1.2830799870007468, "count": 10, "self": 1.2830799870007468 } } }, "_update_policy": { "total": 302.5856625330007, "count": 97, "self": 240.92872617900514, "children": { "TorchPPOOptimizer.update": { "total": 61.65693635399555, "count": 2910, "self": 61.65693635399555 } } } } } } }, "trainer_threads": { "total": 9.529999260848854e-07, "count": 1, "self": 9.529999260848854e-07 }, "TrainerController._save_models": { "total": 0.11263901899974371, "count": 1, "self": 0.0018738779995146615, "children": { "RLTrainer._checkpoint": { "total": 0.11076514100022905, "count": 1, "self": 0.11076514100022905 } } } } } } }