{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.25519952178001404, "min": 0.25519952178001404, "max": 1.507735013961792, "count": 50 }, "Pyramids.Policy.Entropy.sum": { "value": 7660.06884765625, "min": 7660.06884765625, "max": 45738.6484375, "count": 50 }, "Pyramids.Step.mean": { "value": 1499969.0, "min": 29952.0, "max": 1499969.0, "count": 50 }, "Pyramids.Step.sum": { "value": 1499969.0, "min": 29952.0, "max": 1499969.0, "count": 50 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.7191459536552429, "min": -0.20383356511592865, "max": 0.7642956972122192, "count": 50 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 209.27146911621094, "min": -48.308555603027344, "max": 225.98703002929688, "count": 50 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.008622136898338795, "min": -0.005224581342190504, "max": 0.17947332561016083, "count": 50 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 2.5090417861938477, "min": -1.4054124355316162, "max": 43.25307083129883, "count": 50 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06876598556212303, "min": 0.06619945894427863, "max": 0.07509747324816306, "count": 50 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9627237978697225, "min": 0.4826500198202363, "max": 1.0560603594155205, "count": 50 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014195390860896582, "min": 0.00025354069755202896, "max": 0.016918257336198752, "count": 50 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.19873547205255215, "min": 0.002281866277968261, "max": 0.23685560270678252, "count": 50 }, "Pyramids.Policy.LearningRate.mean": { "value": 4.862051408561903e-06, "min": 4.862051408561903e-06, "max": 0.0004946118106014476, "count": 50 }, "Pyramids.Policy.LearningRate.sum": { "value": 6.806871971986664e-05, "min": 6.806871971986664e-05, "max": 0.005789131475507066, "count": 50 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10097239047619049, "min": 0.10097239047619049, "max": 0.19892236190476195, "count": 50 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4136134666666669, "min": 1.3924565333333336, "max": 2.5341676, "count": 50 }, "Pyramids.Policy.Beta.mean": { "value": 0.00010714180857142857, "min": 0.00010714180857142857, "max": 0.009892343954285714, "count": 50 }, "Pyramids.Policy.Beta.sum": { "value": 0.00149998532, "min": 0.00149998532, "max": 0.11579684404, "count": 50 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.006304349284619093, "min": 0.006296868436038494, "max": 0.3404395580291748, "count": 50 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.08826088905334473, "min": 0.08815615624189377, "max": 2.3830769062042236, "count": 50 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 253.38738738738738, "min": 248.8695652173913, "max": 999.0, "count": 50 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28126.0, "min": 15984.0, "max": 33954.0, "count": 50 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7285909852734558, "min": -1.0000000521540642, "max": 1.7474482605426476, "count": 50 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 191.87359936535358, "min": -31.999601677060127, "max": 202.70399822294712, "count": 50 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7285909852734558, "min": -1.0000000521540642, "max": 1.7474482605426476, "count": 50 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 191.87359936535358, "min": -31.999601677060127, "max": 202.70399822294712, "count": 50 }, "Pyramids.Policy.RndReward.mean": { "value": 0.016544496374302293, "min": 0.016544496374302293, "max": 6.33722314145416, "count": 50 }, "Pyramids.Policy.RndReward.sum": { "value": 1.8364390975475544, "min": 1.8364390975475544, "max": 101.39557026326656, "count": 50 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 50 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 50 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1733126923", "python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn /content/ml-agents/config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.5.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1733130543" }, "total": 3619.9356091740005, "count": 1, "self": 0.47713947400006873, "children": { "run_training.setup": { "total": 0.05467897200014704, "count": 1, "self": 0.05467897200014704 }, "TrainerController.start_learning": { "total": 3619.4037907280003, "count": 1, "self": 2.037542858915913, "children": { "TrainerController._reset_env": { "total": 2.1741144920001716, "count": 1, "self": 2.1741144920001716 }, "TrainerController.advance": { "total": 3615.095241216084, "count": 96454, "self": 2.0633117434745145, "children": { "env_step": { "total": 2566.4367558757344, "count": 96454, "self": 2338.336956587837, "children": { "SubprocessEnvManager._take_step": { "total": 226.86999453888075, "count": 96454, "self": 6.902064731917108, "children": { "TorchPolicy.evaluate": { "total": 219.96792980696364, "count": 93822, "self": 219.96792980696364 } } }, "workers": { "total": 1.2298047490166937, "count": 96454, "self": 0.0, "children": { "worker_root": { "total": 3611.501473504934, "count": 96454, "is_parallel": true, "self": 1450.12160218689, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002171154999814462, "count": 1, "is_parallel": true, "self": 0.000683885999933409, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014872689998810529, "count": 8, "is_parallel": true, "self": 0.0014872689998810529 } } }, "UnityEnvironment.step": { "total": 0.04667896999990262, "count": 1, "is_parallel": true, "self": 0.0006524909999825468, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004970850000063365, "count": 1, "is_parallel": true, "self": 0.0004970850000063365 }, "communicator.exchange": { "total": 0.04373528599990095, "count": 1, "is_parallel": true, "self": 0.04373528599990095 }, "steps_from_proto": { "total": 0.001794108000012784, "count": 1, "is_parallel": true, "self": 0.0003905599992322095, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014035480007805745, "count": 8, "is_parallel": true, "self": 0.0014035480007805745 } } } } } } }, "UnityEnvironment.step": { "total": 2161.379871318044, "count": 96453, "is_parallel": true, "self": 49.48082861114881, "children": { "UnityEnvironment._generate_step_input": { "total": 35.46489076085754, "count": 96453, "is_parallel": true, "self": 35.46489076085754 }, "communicator.exchange": { "total": 1927.1353914480005, "count": 96453, "is_parallel": true, "self": 1927.1353914480005 }, "steps_from_proto": { "total": 149.29876049803715, "count": 96453, "is_parallel": true, "self": 30.368113083982735, "children": { "_process_rank_one_or_two_observation": { "total": 118.93064741405442, "count": 771624, "is_parallel": true, "self": 118.93064741405442 } } } } } } } } } } }, "trainer_advance": { "total": 1046.5951735968752, "count": 96454, "self": 3.9710457098126426, "children": { "process_trajectory": { "total": 202.47510914807935, "count": 96454, "self": 202.18510953707982, "children": { "RLTrainer._checkpoint": { "total": 0.28999961099953, "count": 3, "self": 0.28999961099953 } } }, "_update_policy": { "total": 840.1490187389832, "count": 681, "self": 468.3859554219439, "children": { "TorchPPOOptimizer.update": { "total": 371.76306331703927, "count": 34263, "self": 371.76306331703927 } } } } } } }, "trainer_threads": { "total": 1.0769999789772555e-06, "count": 1, "self": 1.0769999789772555e-06 }, "TrainerController._save_models": { "total": 0.09689108400016266, "count": 1, "self": 0.0015178260000539012, "children": { "RLTrainer._checkpoint": { "total": 0.09537325800010876, "count": 1, "self": 0.09537325800010876 } } } } } } }