{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3066169023513794, "min": 0.3066169023513794, "max": 1.3789076805114746, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 9227.9423828125, "min": 9227.9423828125, "max": 41830.54296875, "count": 33 }, "Pyramids.Step.mean": { "value": 989945.0, "min": 29952.0, "max": 989945.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989945.0, "min": 29952.0, "max": 989945.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.4016954004764557, "min": -0.10303453356027603, "max": 0.5250108242034912, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 106.44927978515625, "min": -25.037391662597656, "max": 141.7529296875, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.015544491820037365, "min": 0.015544491820037365, "max": 0.4228117763996124, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 4.119290351867676, "min": 4.119290351867676, "max": 101.47482299804688, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06721175381237826, "min": 0.06680049433958904, "max": 0.07317832606249974, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9409645533732957, "min": 0.4846738576865621, "max": 1.0711812295399687, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01637236510693795, "min": 0.0002342853779435526, "max": 0.01637236510693795, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2292131114971313, "min": 0.0016399976456048682, "max": 0.2292131114971313, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.632376027335713e-06, "min": 7.632376027335713e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010685326438269998, "min": 0.00010685326438269998, "max": 0.0036335101888299993, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10254409285714286, "min": 0.10254409285714286, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4356173, "min": 1.3691136000000002, "max": 2.6111700000000004, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026415487642857143, "min": 0.00026415487642857143, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.00369816827, "min": 0.00369816827, "max": 0.12113588299999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.016234682872891426, "min": 0.015581890009343624, "max": 0.6096732020378113, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.22728556394577026, "min": 0.21962903439998627, "max": 4.267712593078613, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 411.0133333333333, "min": 365.4457831325301, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30826.0, "min": 15984.0, "max": 32100.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5089626328150432, "min": -1.0000000521540642, "max": 1.5089626328150432, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 113.17219746112823, "min": -32.000001668930054, "max": 125.08679831027985, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5089626328150432, "min": -1.0000000521540642, "max": 1.5089626328150432, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 113.17219746112823, "min": -32.000001668930054, "max": 125.08679831027985, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.0692547274264507, "min": 0.06618939946366555, "max": 12.051612592302263, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 5.1941045569838025, "min": 4.898015560311251, "max": 192.8258014768362, "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": "1733342376", "python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./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": "1733344720" }, "total": 2343.501727905, "count": 1, "self": 0.5334934140005316, "children": { "run_training.setup": { "total": 0.053587187999710295, "count": 1, "self": 0.053587187999710295 }, "TrainerController.start_learning": { "total": 2342.9146473029996, "count": 1, "self": 1.4689502372061725, "children": { "TrainerController._reset_env": { "total": 2.1897057910000512, "count": 1, "self": 2.1897057910000512 }, "TrainerController.advance": { "total": 2339.155841470794, "count": 63754, "self": 1.4518742527607174, "children": { "env_step": { "total": 1612.0244541850202, "count": 63754, "self": 1449.4652082610473, "children": { "SubprocessEnvManager._take_step": { "total": 161.70888720895937, "count": 63754, "self": 4.763653314032126, "children": { "TorchPolicy.evaluate": { "total": 156.94523389492724, "count": 62547, "self": 156.94523389492724 } } }, "workers": { "total": 0.850358715013499, "count": 63754, "self": 0.0, "children": { "worker_root": { "total": 2337.703562867083, "count": 63754, "is_parallel": true, "self": 1008.5613253529204, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00224349300015092, "count": 1, "is_parallel": true, "self": 0.0007218790001388697, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015216140000120504, "count": 8, "is_parallel": true, "self": 0.0015216140000120504 } } }, "UnityEnvironment.step": { "total": 0.05336700599991673, "count": 1, "is_parallel": true, "self": 0.0006807159998061252, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000504229999933159, "count": 1, "is_parallel": true, "self": 0.000504229999933159 }, "communicator.exchange": { "total": 0.050325426000199514, "count": 1, "is_parallel": true, "self": 0.050325426000199514 }, "steps_from_proto": { "total": 0.0018566339999779302, "count": 1, "is_parallel": true, "self": 0.0003925750011148921, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014640589988630381, "count": 8, "is_parallel": true, "self": 0.0014640589988630381 } } } } } } }, "UnityEnvironment.step": { "total": 1329.1422375141624, "count": 63753, "is_parallel": true, "self": 33.87937344425518, "children": { "UnityEnvironment._generate_step_input": { "total": 23.62778359092681, "count": 63753, "is_parallel": true, "self": 23.62778359092681 }, "communicator.exchange": { "total": 1170.3101568760062, "count": 63753, "is_parallel": true, "self": 1170.3101568760062 }, "steps_from_proto": { "total": 101.3249236029742, "count": 63753, "is_parallel": true, "self": 20.733359154840855, "children": { "_process_rank_one_or_two_observation": { "total": 80.59156444813334, "count": 510024, "is_parallel": true, "self": 80.59156444813334 } } } } } } } } } } }, "trainer_advance": { "total": 725.6795130330129, "count": 63754, "self": 2.744650358074068, "children": { "process_trajectory": { "total": 139.99499581493728, "count": 63754, "self": 139.7696843179374, "children": { "RLTrainer._checkpoint": { "total": 0.22531149699989328, "count": 2, "self": 0.22531149699989328 } } }, "_update_policy": { "total": 582.9398668600015, "count": 448, "self": 307.69381706401236, "children": { "TorchPPOOptimizer.update": { "total": 275.24604979598917, "count": 22815, "self": 275.24604979598917 } } } } } } }, "trainer_threads": { "total": 1.3030003174208105e-06, "count": 1, "self": 1.3030003174208105e-06 }, "TrainerController._save_models": { "total": 0.10014850099923933, "count": 1, "self": 0.002238267999018717, "children": { "RLTrainer._checkpoint": { "total": 0.09791023300022061, "count": 1, "self": 0.09791023300022061 } } } } } } }