{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.1448037028312683, "min": 0.141936793923378, "max": 1.4616410732269287, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 4381.1806640625, "min": 4264.9169921875, "max": 44340.34375, "count": 100 }, "Pyramids.Step.mean": { "value": 2999925.0, "min": 29952.0, "max": 2999925.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999925.0, "min": 29952.0, "max": 2999925.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.8441714644432068, "min": -0.07762841880321503, "max": 0.9022995233535767, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 259.16064453125, "min": -18.78607749938965, "max": 277.5233154296875, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.02148943953216076, "min": -0.0177775789052248, "max": 0.17452770471572876, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 6.5972580909729, "min": -5.297718524932861, "max": 42.06117630004883, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06744033093578071, "min": 0.06288980718818493, "max": 0.07413494269019881, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.94416463310093, "min": 0.5019719198516077, "max": 1.0619254687301103, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015236293144490837, "min": 0.0008293041496231138, "max": 0.01697138737446429, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21330810402287173, "min": 0.009951649795477366, "max": 0.2460696250879361, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.4328852366904721e-06, "min": 1.4328852366904721e-06, "max": 0.00029838354339596195, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.006039331366661e-05, "min": 2.006039331366661e-05, "max": 0.004072205742598133, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10047759523809523, "min": 0.10047759523809523, "max": 0.19946118095238097, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4066863333333333, "min": 1.3962282666666668, "max": 2.857401866666667, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 5.771176428571416e-05, "min": 5.771176428571416e-05, "max": 0.009946171977142856, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.0008079646999999983, "min": 0.0008079646999999983, "max": 0.13575444647999999, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.005396395921707153, "min": 0.00536471139639616, "max": 0.3215520977973938, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.07554954290390015, "min": 0.07510595768690109, "max": 2.2508647441864014, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 198.48, "min": 187.71428571428572, "max": 999.0, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29772.0, "min": 15984.0, "max": 34187.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.8015199895699818, "min": -1.0000000521540642, "max": 1.8122857042721339, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 270.2279984354973, "min": -30.572601683437824, "max": 291.77799838781357, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.8015199895699818, "min": -1.0000000521540642, "max": 1.8122857042721339, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 270.2279984354973, "min": -30.572601683437824, "max": 291.77799838781357, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.011200727632797983, "min": 0.011200727632797983, "max": 6.818409530445933, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 1.6801091449196974, "min": 1.6172916853247443, "max": 109.09455248713493, "count": 100 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1675531928", "python_version": "3.8.0 (default, Nov 6 2019, 21:49:08) \n[GCC 7.3.0]", "command_line_arguments": "/home/sebas/miniconda3/envs/RL-unity/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics", "mlagents_version": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.19.0", "end_time_seconds": "1675535901" }, "total": 3972.9241316244006, "count": 1, "self": 0.21836111973971128, "children": { "run_training.setup": { "total": 0.007066701538860798, "count": 1, "self": 0.007066701538860798 }, "TrainerController.start_learning": { "total": 3972.698703803122, "count": 1, "self": 2.87083085719496, "children": { "TrainerController._reset_env": { "total": 2.497703865170479, "count": 1, "self": 2.497703865170479 }, "TrainerController.advance": { "total": 3967.2729753339663, "count": 195910, "self": 2.7857416067272425, "children": { "env_step": { "total": 2247.6482253037393, "count": 195910, "self": 1934.484874160029, "children": { "SubprocessEnvManager._take_step": { "total": 311.32023830525577, "count": 195910, "self": 7.89780777040869, "children": { "TorchPolicy.evaluate": { "total": 303.4224305348471, "count": 187563, "self": 146.20217437669635, "children": { "TorchPolicy.sample_actions": { "total": 157.22025615815073, "count": 187563, "self": 157.22025615815073 } } } } }, "workers": { "total": 1.8431128384545445, "count": 195910, "self": 0.0, "children": { "worker_root": { "total": 3968.302522957325, "count": 195910, "is_parallel": true, "self": 2231.5719877462834, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0012293597683310509, "count": 1, "is_parallel": true, "self": 0.0002886941656470299, "children": { "_process_rank_one_or_two_observation": { "total": 0.000940665602684021, "count": 8, "is_parallel": true, "self": 0.000940665602684021 } } }, "UnityEnvironment.step": { "total": 0.020653321407735348, "count": 1, "is_parallel": true, "self": 0.00021353457123041153, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0001868894323706627, "count": 1, "is_parallel": true, "self": 0.0001868894323706627 }, "communicator.exchange": { "total": 0.019312528893351555, "count": 1, "is_parallel": true, "self": 0.019312528893351555 }, "steps_from_proto": { "total": 0.0009403685107827187, "count": 1, "is_parallel": true, "self": 0.0001743873581290245, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007659811526536942, "count": 8, "is_parallel": true, "self": 0.0007659811526536942 } } } } } } }, "UnityEnvironment.step": { "total": 1736.7305352110416, "count": 195909, "is_parallel": true, "self": 53.00903392583132, "children": { "UnityEnvironment._generate_step_input": { "total": 29.23957723658532, "count": 195909, "is_parallel": true, "self": 29.23957723658532 }, "communicator.exchange": { "total": 1433.453662076965, "count": 195909, "is_parallel": true, "self": 1433.453662076965 }, "steps_from_proto": { "total": 221.02826197165996, "count": 195909, "is_parallel": true, "self": 31.13885751925409, "children": { "_process_rank_one_or_two_observation": { "total": 189.88940445240587, "count": 1567272, "is_parallel": true, "self": 189.88940445240587 } } } } } } } } } } }, "trainer_advance": { "total": 1716.8390084234998, "count": 195910, "self": 5.1214051945135, "children": { "process_trajectory": { "total": 378.6552766310051, "count": 195910, "self": 378.24057990219444, "children": { "RLTrainer._checkpoint": { "total": 0.414696728810668, "count": 6, "self": 0.414696728810668 } } }, "_update_policy": { "total": 1333.0623265979812, "count": 1402, "self": 476.2830830384046, "children": { "TorchPPOOptimizer.update": { "total": 856.7792435595766, "count": 68376, "self": 856.7792435595766 } } } } } } }, "trainer_threads": { "total": 6.51925802230835e-07, "count": 1, "self": 6.51925802230835e-07 }, "TrainerController._save_models": { "total": 0.05719309486448765, "count": 1, "self": 0.0007409965619444847, "children": { "RLTrainer._checkpoint": { "total": 0.05645209830254316, "count": 1, "self": 0.05645209830254316 } } } } } } }