{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5859135389328003, "min": 0.5413445234298706, "max": 1.4530715942382812, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 17689.90234375, "min": 16352.935546875, "max": 44080.37890625, "count": 33 }, "Pyramids.Step.mean": { "value": 989877.0, "min": 29957.0, "max": 989877.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989877.0, "min": 29957.0, "max": 989877.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.3029424846172333, "min": -0.10581455379724503, "max": 0.33697310090065, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 80.27975463867188, "min": -25.395492553710938, "max": 87.61300659179688, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.04876279830932617, "min": -0.09205429255962372, "max": 0.32522737979888916, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -12.922142028808594, "min": -23.93411636352539, "max": 77.40411376953125, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06981077696088635, "min": 0.06430464750750926, "max": 0.07418119198492992, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9773508774524089, "min": 0.47991959456603267, "max": 1.038536687789019, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014555268061009147, "min": 0.00015856312704160477, "max": 0.015174812689009639, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.20377375285412805, "min": 0.002219883778582467, "max": 0.22762219033514458, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.291983283657138e-06, "min": 7.291983283657138e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010208776597119993, "min": 0.00010208776597119993, "max": 0.0036330673889776, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10243062857142858, "min": 0.10243062857142858, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4340288, "min": 1.3886848, "max": 2.6110224, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002528197942857141, "min": 0.0002528197942857141, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003539477119999998, "min": 0.003539477119999998, "max": 0.12112113776, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.008271025493741035, "min": 0.008271025493741035, "max": 0.4350031018257141, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1157943531870842, "min": 0.1157943531870842, "max": 3.0450217723846436, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 510.5967741935484, "min": 499.719298245614, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31657.0, "min": 16756.0, "max": 32963.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.2635322305704317, "min": -0.9997419866342698, "max": 1.2635322305704317, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 78.33899829536676, "min": -30.992001585662365, "max": 78.33899829536676, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.2635322305704317, "min": -0.9997419866342698, "max": 1.2635322305704317, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 78.33899829536676, "min": -30.992001585662365, "max": 78.33899829536676, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.044250603103489175, "min": 0.044250603103489175, "max": 8.804327225422158, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.7435373924163287, "min": 2.448151649965439, "max": 149.67356283217669, "count": 33 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 33 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 33 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1785419351", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=/content/training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids1 --no-graphics --force", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1785421600" }, "total": 2248.760261202, "count": 1, "self": 0.4778270660003727, "children": { "run_training.setup": { "total": 0.02572264999980689, "count": 1, "self": 0.02572264999980689 }, "TrainerController.start_learning": { "total": 2248.256711486, "count": 1, "self": 1.3437813750356327, "children": { "TrainerController._reset_env": { "total": 2.141244170000391, "count": 1, "self": 2.141244170000391 }, "TrainerController.advance": { "total": 2244.6913465639636, "count": 63307, "self": 1.382978213819115, "children": { "env_step": { "total": 1612.262014530062, "count": 63307, "self": 1457.5759160170264, "children": { "SubprocessEnvManager._take_step": { "total": 153.85097786514098, "count": 63307, "self": 4.710484057156918, "children": { "TorchPolicy.evaluate": { "total": 149.14049380798406, "count": 62565, "self": 149.14049380798406 } } }, "workers": { "total": 0.8351206478946551, "count": 63307, "self": 0.0, "children": { "worker_root": { "total": 2242.508382499888, "count": 63307, "is_parallel": true, "self": 902.7247499950327, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0019269939998594054, "count": 1, "is_parallel": true, "self": 0.0006081599995013676, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013188340003580379, "count": 8, "is_parallel": true, "self": 0.0013188340003580379 } } }, "UnityEnvironment.step": { "total": 0.06108848400026545, "count": 1, "is_parallel": true, "self": 0.000552803000118729, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004944649999742978, "count": 1, "is_parallel": true, "self": 0.0004944649999742978 }, "communicator.exchange": { "total": 0.05828676600003746, "count": 1, "is_parallel": true, "self": 0.05828676600003746 }, "steps_from_proto": { "total": 0.001754450000134966, "count": 1, "is_parallel": true, "self": 0.0004064800004925928, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013479699996423733, "count": 8, "is_parallel": true, "self": 0.0013479699996423733 } } } } } } }, "UnityEnvironment.step": { "total": 1339.7836325048552, "count": 63306, "is_parallel": true, "self": 34.37201086276582, "children": { "UnityEnvironment._generate_step_input": { "total": 23.9645577120682, "count": 63306, "is_parallel": true, "self": 23.9645577120682 }, "communicator.exchange": { "total": 1171.6464554059457, "count": 63306, "is_parallel": true, "self": 1171.6464554059457 }, "steps_from_proto": { "total": 109.80060852407541, "count": 63306, "is_parallel": true, "self": 22.80125354906295, "children": { "_process_rank_one_or_two_observation": { "total": 86.99935497501247, "count": 506448, "is_parallel": true, "self": 86.99935497501247 } } } } } } } } } } }, "trainer_advance": { "total": 631.0463538200825, "count": 63307, "self": 2.621943866116453, "children": { "process_trajectory": { "total": 110.09371024597294, "count": 63307, "self": 109.8389200339725, "children": { "RLTrainer._checkpoint": { "total": 0.2547902120004437, "count": 2, "self": 0.2547902120004437 } } }, "_update_policy": { "total": 518.3306997079931, "count": 452, "self": 276.2085402730172, "children": { "TorchPPOOptimizer.update": { "total": 242.12215943497586, "count": 22770, "self": 242.12215943497586 } } } } } } }, "trainer_threads": { "total": 8.699998943484388e-07, "count": 1, "self": 8.699998943484388e-07 }, "TrainerController._save_models": { "total": 0.08033850700030598, "count": 1, "self": 0.0012109850003980682, "children": { "RLTrainer._checkpoint": { "total": 0.07912752199990791, "count": 1, "self": 0.07912752199990791 } } } } } } }