{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.22929097712039948, "min": 0.22147920727729797, "max": 1.4221351146697998, "count": 50 }, "Pyramids.Policy.Entropy.sum": { "value": 6838.3740234375, "min": 6690.44384765625, "max": 43141.890625, "count": 50 }, "Pyramids.Step.mean": { "value": 1499980.0, "min": 29952.0, "max": 1499980.0, "count": 50 }, "Pyramids.Step.sum": { "value": 1499980.0, "min": 29952.0, "max": 1499980.0, "count": 50 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.7262492179870605, "min": -0.12259096652269363, "max": 0.7778822183609009, "count": 50 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 212.791015625, "min": -29.544422149658203, "max": 229.47525024414062, "count": 50 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.017438266426324844, "min": -0.03241197392344475, "max": 0.3020504117012024, "count": 50 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 5.10941219329834, "min": -8.62158489227295, "max": 71.58594512939453, "count": 50 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06806238504941575, "min": 0.06455917499456633, "max": 0.0738861463420714, "count": 50 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9528733906918205, "min": 0.4872314462469337, "max": 1.0771813474888867, "count": 50 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014367812083773536, "min": 9.688859022965231e-05, "max": 0.01645606311822554, "count": 50 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2011493691728295, "min": 0.0013564402632151324, "max": 0.24551326486135963, "count": 50 }, "Pyramids.Policy.LearningRate.mean": { "value": 3.1416703813809517e-06, "min": 3.1416703813809517e-06, "max": 0.00029676708679192377, "count": 50 }, "Pyramids.Policy.LearningRate.sum": { "value": 4.398338533933333e-05, "min": 4.398338533933333e-05, "max": 0.0036545653818115995, "count": 50 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10104719047619048, "min": 0.10104719047619048, "max": 0.19892236190476195, "count": 50 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4146606666666668, "min": 1.3794090666666667, "max": 2.6181884000000006, "count": 50 }, "Pyramids.Policy.Beta.mean": { "value": 0.00011461432857142858, "min": 0.00011461432857142858, "max": 0.009892343954285714, "count": 50 }, "Pyramids.Policy.Beta.sum": { "value": 0.0016046006, "min": 0.0016046006, "max": 0.12183702115999999, "count": 50 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010168899782001972, "min": 0.010024704039096832, "max": 0.45344170928001404, "count": 50 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.14236459136009216, "min": 0.14034585654735565, "max": 3.1740920543670654, "count": 50 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 251.75, "min": 228.50393700787401, "max": 999.0, "count": 50 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30210.0, "min": 15984.0, "max": 32781.0, "count": 50 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7494297351472634, "min": -1.0000000521540642, "max": 1.770267701759113, "count": 50 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 211.68099795281887, "min": -32.000001668930054, "max": 224.82399812340736, "count": 50 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7494297351472634, "min": -1.0000000521540642, "max": 1.770267701759113, "count": 50 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 211.68099795281887, "min": -32.000001668930054, "max": 224.82399812340736, "count": 50 }, "Pyramids.Policy.RndReward.mean": { "value": 0.02620454387095168, "min": 0.024720477220198087, "max": 9.579654056578875, "count": 50 }, "Pyramids.Policy.RndReward.sum": { "value": 3.1707498083851533, "min": 3.0282883491308894, "max": 153.274464905262, "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": "1685866891", "python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [GCC 9.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=PyramidsRND --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": "1685870442" }, "total": 3550.9206053549997, "count": 1, "self": 0.5753164249999827, "children": { "run_training.setup": { "total": 0.042803211999853374, "count": 1, "self": 0.042803211999853374 }, "TrainerController.start_learning": { "total": 3550.302485718, "count": 1, "self": 2.2334032709973144, "children": { "TrainerController._reset_env": { "total": 3.6784017749996565, "count": 1, "self": 3.6784017749996565 }, "TrainerController.advance": { "total": 3544.291227039002, "count": 96710, "self": 2.2578433160128952, "children": { "env_step": { "total": 2607.718581934908, "count": 96710, "self": 2435.4058637560693, "children": { "SubprocessEnvManager._take_step": { "total": 170.97957328087705, "count": 96710, "self": 7.344103831932443, "children": { "TorchPolicy.evaluate": { "total": 163.6354694489446, "count": 93814, "self": 163.6354694489446 } } }, "workers": { "total": 1.3331448979615743, "count": 96710, "self": 0.0, "children": { "worker_root": { "total": 3542.1563782999174, "count": 96710, "is_parallel": true, "self": 1285.950373642822, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018310929999643122, "count": 1, "is_parallel": true, "self": 0.0005710499990527751, "children": { "_process_rank_one_or_two_observation": { "total": 0.001260043000911537, "count": 8, "is_parallel": true, "self": 0.001260043000911537 } } }, "UnityEnvironment.step": { "total": 0.04741607699997985, "count": 1, "is_parallel": true, "self": 0.0005924960005359026, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005117929999869375, "count": 1, "is_parallel": true, "self": 0.0005117929999869375 }, "communicator.exchange": { "total": 0.044369594999807305, "count": 1, "is_parallel": true, "self": 0.044369594999807305 }, "steps_from_proto": { "total": 0.0019421929996497056, "count": 1, "is_parallel": true, "self": 0.00039331900097749894, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015488739986722067, "count": 8, "is_parallel": true, "self": 0.0015488739986722067 } } } } } } }, "UnityEnvironment.step": { "total": 2256.2060046570955, "count": 96709, "is_parallel": true, "self": 50.8518132531608, "children": { "UnityEnvironment._generate_step_input": { "total": 36.58727748590809, "count": 96709, "is_parallel": true, "self": 36.58727748590809 }, "communicator.exchange": { "total": 2006.9956509900571, "count": 96709, "is_parallel": true, "self": 2006.9956509900571 }, "steps_from_proto": { "total": 161.77126292796947, "count": 96709, "is_parallel": true, "self": 33.15267456284437, "children": { "_process_rank_one_or_two_observation": { "total": 128.6185883651251, "count": 773672, "is_parallel": true, "self": 128.6185883651251 } } } } } } } } } } }, "trainer_advance": { "total": 934.3148017880812, "count": 96710, "self": 4.4016466042608045, "children": { "process_trajectory": { "total": 170.44975956981625, "count": 96710, "self": 170.0590800878158, "children": { "RLTrainer._checkpoint": { "total": 0.39067948200045066, "count": 3, "self": 0.39067948200045066 } } }, "_update_policy": { "total": 759.4633956140042, "count": 683, "self": 485.4348679558998, "children": { "TorchPPOOptimizer.update": { "total": 274.0285276581044, "count": 34194, "self": 274.0285276581044 } } } } } } }, "trainer_threads": { "total": 1.0680005289032124e-06, "count": 1, "self": 1.0680005289032124e-06 }, "TrainerController._save_models": { "total": 0.09945256500031974, "count": 1, "self": 0.001604840000254626, "children": { "RLTrainer._checkpoint": { "total": 0.09784772500006511, "count": 1, "self": 0.09784772500006511 } } } } } } }