{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4008711576461792, "min": 1.4008711576461792, "max": 1.426134467124939, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 69728.359375, "min": 68687.3125, "max": 77113.0703125, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 114.31639722863741, "min": 95.25925925925925, "max": 418.46666666666664, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49499.0, "min": 48868.0, "max": 50216.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999968.0, "min": 49784.0, "max": 1999968.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999968.0, "min": 49784.0, "max": 1999968.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.265256881713867, "min": 0.02804151177406311, "max": 2.3793020248413086, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 980.856201171875, "min": 3.336939811706543, "max": 1225.340576171875, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.440291326536042, "min": 1.9523881213003849, "max": 3.806537246729041, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1489.6461443901062, "min": 232.3341864347458, "max": 1931.1817138195038, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.440291326536042, "min": 1.9523881213003849, "max": 3.806537246729041, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1489.6461443901062, "min": 232.3341864347458, "max": 1931.1817138195038, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.016039998892423076, "min": 0.013997945417941082, "max": 0.02081113938281002, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.03207999778484615, "min": 0.027995890835882165, "max": 0.054642028703043855, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.047516550434132415, "min": 0.02287727287039161, "max": 0.058632809979220234, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.09503310086826483, "min": 0.04575454574078322, "max": 0.17060615780452887, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 4.3151485616499985e-06, "min": 4.3151485616499985e-06, "max": 0.000295356526547825, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 8.630297123299997e-06, "min": 8.630297123299997e-06, "max": 0.0008439003186998999, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10143835000000001, "min": 0.10143835000000001, "max": 0.19845217500000006, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.20287670000000002, "min": 0.20287670000000002, "max": 0.5813001, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 8.177366499999998e-05, "min": 8.177366499999998e-05, "max": 0.004922763532499999, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00016354732999999995, "min": 0.00016354732999999995, "max": 0.014066874990000002, "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": "1704032183", "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=Huggy --no-graphics --resume", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.2+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1704034763" }, "total": 2580.459087127, "count": 1, "self": 0.48733696900035284, "children": { "run_training.setup": { "total": 0.055922561999977916, "count": 1, "self": 0.055922561999977916 }, "TrainerController.start_learning": { "total": 2579.915827596, "count": 1, "self": 4.601503864885217, "children": { "TrainerController._reset_env": { "total": 2.0709349889999658, "count": 1, "self": 2.0709349889999658 }, "TrainerController.advance": { "total": 2573.130983325115, "count": 231123, "self": 4.941738916047598, "children": { "env_step": { "total": 2042.1962950150416, "count": 231123, "self": 1698.0216546849451, "children": { "SubprocessEnvManager._take_step": { "total": 341.1554239121117, "count": 231123, "self": 18.380907190096536, "children": { "TorchPolicy.evaluate": { "total": 322.77451672201516, "count": 222928, "self": 322.77451672201516 } } }, "workers": { "total": 3.0192164179849215, "count": 231123, "self": 0.0, "children": { "worker_root": { "total": 2572.4518016360366, "count": 231123, "is_parallel": true, "self": 1186.3080689079966, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0006303340001068136, "count": 1, "is_parallel": true, "self": 0.00019268800008376274, "children": { "_process_rank_one_or_two_observation": { "total": 0.0004376460000230509, "count": 2, "is_parallel": true, "self": 0.0004376460000230509 } } }, "UnityEnvironment.step": { "total": 0.03121718200009127, "count": 1, "is_parallel": true, "self": 0.00031832500019390864, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00020391099997141282, "count": 1, "is_parallel": true, "self": 0.00020391099997141282 }, "communicator.exchange": { "total": 0.029928049999966788, "count": 1, "is_parallel": true, "self": 0.029928049999966788 }, "steps_from_proto": { "total": 0.0007668959999591607, "count": 1, "is_parallel": true, "self": 0.00022709199993187212, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005398040000272886, "count": 2, "is_parallel": true, "self": 0.0005398040000272886 } } } } } } }, "UnityEnvironment.step": { "total": 1386.14373272804, "count": 231122, "is_parallel": true, "self": 42.616094912980316, "children": { "UnityEnvironment._generate_step_input": { "total": 87.53505541899983, "count": 231122, "is_parallel": true, "self": 87.53505541899983 }, "communicator.exchange": { "total": 1160.3804052050684, "count": 231122, "is_parallel": true, "self": 1160.3804052050684 }, "steps_from_proto": { "total": 95.61217719099147, "count": 231122, "is_parallel": true, "self": 33.8377296129529, "children": { "_process_rank_one_or_two_observation": { "total": 61.774447578038576, "count": 462244, "is_parallel": true, "self": 61.774447578038576 } } } } } } } } } } }, "trainer_advance": { "total": 525.9929493940257, "count": 231123, "self": 7.199118812009374, "children": { "process_trajectory": { "total": 151.83757886301714, "count": 231123, "self": 150.43003078501704, "children": { "RLTrainer._checkpoint": { "total": 1.4075480780001044, "count": 10, "self": 1.4075480780001044 } } }, "_update_policy": { "total": 366.95625171899917, "count": 96, "self": 299.1023154189961, "children": { "TorchPPOOptimizer.update": { "total": 67.85393630000306, "count": 2880, "self": 67.85393630000306 } } } } } } }, "trainer_threads": { "total": 9.300001693191007e-07, "count": 1, "self": 9.300001693191007e-07 }, "TrainerController._save_models": { "total": 0.11240448699982153, "count": 1, "self": 0.003107309999904828, "children": { "RLTrainer._checkpoint": { "total": 0.1092971769999167, "count": 1, "self": 0.1092971769999167 } } } } } } }