{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 1.365854263305664, "min": 1.365854263305664, "max": 1.365854263305664, "count": 1 }, "Pyramids.Policy.Entropy.sum": { "value": 41434.5546875, "min": 41434.5546875, "max": 41434.5546875, "count": 1 }, "Pyramids.Step.mean": { "value": 29952.0, "min": 29952.0, "max": 29952.0, "count": 1 }, "Pyramids.Step.sum": { "value": 29952.0, "min": 29952.0, "max": 29952.0, "count": 1 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": -0.09646448493003845, "min": -0.09646448493003845, "max": -0.09646448493003845, "count": 1 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": -22.862083435058594, "min": -22.862083435058594, "max": -22.862083435058594, "count": 1 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.5087708234786987, "min": 0.5087708234786987, "max": 0.5087708234786987, "count": 1 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 120.57868957519531, "min": 120.57868957519531, "max": 120.57868957519531, "count": 1 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07360291886027258, "min": 0.07360291886027258, "max": 0.07360291886027258, "count": 1 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.515220432021908, "min": 0.515220432021908, "max": 0.515220432021908, "count": 1 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.028243492458447986, "min": 0.028243492458447986, "max": 0.028243492458447986, "count": 1 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.1977044472091359, "min": 0.1977044472091359, "max": 0.1977044472091359, "count": 1 }, "Pyramids.Policy.LearningRate.mean": { "value": 0.00029838354339596195, "min": 0.00029838354339596195, "max": 0.00029838354339596195, "count": 1 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0020886848037717336, "min": 0.0020886848037717336, "max": 0.0020886848037717336, "count": 1 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.19946118095238097, "min": 0.19946118095238097, "max": 0.19946118095238097, "count": 1 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.3962282666666668, "min": 1.3962282666666668, "max": 1.3962282666666668, "count": 1 }, "Pyramids.Policy.Beta.mean": { "value": 0.009946171977142856, "min": 0.009946171977142856, "max": 0.009946171977142856, "count": 1 }, "Pyramids.Policy.Beta.sum": { "value": 0.06962320384, "min": 0.06962320384, "max": 0.06962320384, "count": 1 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.820715069770813, "min": 0.820715069770813, "max": 0.820715069770813, "count": 1 }, "Pyramids.Losses.RNDLoss.sum": { "value": 5.7450056076049805, "min": 5.7450056076049805, "max": 5.7450056076049805, "count": 1 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 999.0, "min": 999.0, "max": 999.0, "count": 1 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 15984.0, "min": 15984.0, "max": 15984.0, "count": 1 }, "Pyramids.Environment.CumulativeReward.mean": { "value": -1.0000000521540642, "min": -1.0000000521540642, "max": -1.0000000521540642, "count": 1 }, "Pyramids.Environment.CumulativeReward.sum": { "value": -16.000000834465027, "min": -16.000000834465027, "max": -16.000000834465027, "count": 1 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": -1.0000000521540642, "min": -1.0000000521540642, "max": -1.0000000521540642, "count": 1 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": -16.000000834465027, "min": -16.000000834465027, "max": -16.000000834465027, "count": 1 }, "Pyramids.Policy.RndReward.mean": { "value": 13.97216328792274, "min": 13.97216328792274, "max": 13.97216328792274, "count": 1 }, "Pyramids.Policy.RndReward.sum": { "value": 223.55461260676384, "min": 223.55461260676384, "max": 223.55461260676384, "count": 1 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1692551120", "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/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --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": "1692551265" }, "total": 145.6566251490001, "count": 1, "self": 0.32095980400026747, "children": { "run_training.setup": { "total": 0.05384768799990525, "count": 1, "self": 0.05384768799990525 }, "TrainerController.start_learning": { "total": 145.28181765699992, "count": 1, "self": 0.10309892900340856, "children": { "TrainerController._reset_env": { "total": 1.416397636000056, "count": 1, "self": 1.416397636000056 }, "TrainerController.advance": { "total": 143.54564729399635, "count": 2980, "self": 0.11768390800466477, "children": { "env_step": { "total": 84.95493832499778, "count": 2980, "self": 78.02855760299053, "children": { "SubprocessEnvManager._take_step": { "total": 6.862815666004735, "count": 2980, "self": 0.3397184679915881, "children": { "TorchPolicy.evaluate": { "total": 6.523097198013147, "count": 2980, "self": 6.523097198013147 } } }, "workers": { "total": 0.06356505600251694, "count": 2979, "self": 0.0, "children": { "worker_root": { "total": 144.83774195298838, "count": 2979, "is_parallel": true, "self": 74.81253386399294, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.003930443999934141, "count": 1, "is_parallel": true, "self": 0.0011897809999936726, "children": { "_process_rank_one_or_two_observation": { "total": 0.0027406629999404686, "count": 8, "is_parallel": true, "self": 0.0027406629999404686 } } }, "UnityEnvironment.step": { "total": 0.07228633799991258, "count": 1, "is_parallel": true, "self": 0.0007304089999706775, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0006043819998922118, "count": 1, "is_parallel": true, "self": 0.0006043819998922118 }, "communicator.exchange": { "total": 0.06842258800020318, "count": 1, "is_parallel": true, "self": 0.06842258800020318 }, "steps_from_proto": { "total": 0.002528958999846509, "count": 1, "is_parallel": true, "self": 0.0004882100001850631, "children": { "_process_rank_one_or_two_observation": { "total": 0.002040748999661446, "count": 8, "is_parallel": true, "self": 0.002040748999661446 } } } } } } }, "UnityEnvironment.step": { "total": 70.02520808899544, "count": 2978, "is_parallel": true, "self": 2.1759960220017547, "children": { "UnityEnvironment._generate_step_input": { "total": 1.2280702289867804, "count": 2978, "is_parallel": true, "self": 1.2280702289867804 }, "communicator.exchange": { "total": 60.04638757800399, "count": 2978, "is_parallel": true, "self": 60.04638757800399 }, "steps_from_proto": { "total": 6.574754260002919, "count": 2978, "is_parallel": true, "self": 1.3987937940169104, "children": { "_process_rank_one_or_two_observation": { "total": 5.175960465986009, "count": 23824, "is_parallel": true, "self": 5.175960465986009 } } } } } } } } } } }, "trainer_advance": { "total": 58.473025060993905, "count": 2979, "self": 0.13293337298773622, "children": { "process_trajectory": { "total": 6.859676575005778, "count": 2979, "self": 6.859676575005778 }, "_update_policy": { "total": 51.48041511300039, "count": 12, "self": 21.87900866100472, "children": { "TorchPPOOptimizer.update": { "total": 29.601406451995672, "count": 1086, "self": 29.601406451995672 } } } } } } }, "trainer_threads": { "total": 2.0420000055310084e-06, "count": 1, "self": 2.0420000055310084e-06 }, "TrainerController._save_models": { "total": 0.21667175600009614, "count": 1, "self": 0.0023916350000945386, "children": { "RLTrainer._checkpoint": { "total": 0.2142801210000016, "count": 1, "self": 0.2142801210000016 } } } } } } }