{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3300054967403412, "min": 0.28913331031799316, "max": 1.4054951667785645, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 9815.68359375, "min": 8692.50390625, "max": 42637.1015625, "count": 33 }, "Pyramids.Step.mean": { "value": 989930.0, "min": 29952.0, "max": 989930.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989930.0, "min": 29952.0, "max": 989930.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5283048152923584, "min": -0.11196937412023544, "max": 0.5597864985466003, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 144.75552368164062, "min": -26.984619140625, "max": 154.50106811523438, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.00793149508535862, "min": -0.00793149508535862, "max": 0.65512615442276, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -2.173229694366455, "min": -2.173229694366455, "max": 155.264892578125, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0669418674477419, "min": 0.06586539509826202, "max": 0.07331052535711402, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9371861442683866, "min": 0.4962516708022529, "max": 1.0809047138609456, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.017401353047260818, "min": 0.0005766882140443668, "max": 0.017401353047260818, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.24361894266165143, "min": 0.005766882140443667, "max": 0.24361894266165143, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.202733313407141e-06, "min": 7.202733313407141e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010083826638769998, "min": 0.00010083826638769998, "max": 0.003507029030990399, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10240087857142861, "min": 0.10240087857142861, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4336123000000005, "min": 1.3886848, "max": 2.5725768, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002498477692857143, "min": 0.0002498477692857143, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0034978687700000003, "min": 0.0034978687700000003, "max": 0.11692405903999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.00851180125027895, "min": 0.007902474142611027, "max": 0.48202115297317505, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.11916521936655045, "min": 0.11123988777399063, "max": 3.37414813041687, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 346.8488372093023, "min": 319.88235294117646, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29829.0, "min": 15984.0, "max": 33411.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5378551458319027, "min": -1.0000000521540642, "max": 1.588359078223055, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 133.79339768737555, "min": -30.624601736664772, "max": 139.77559888362885, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5378551458319027, "min": -1.0000000521540642, "max": 1.588359078223055, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 133.79339768737555, "min": -30.624601736664772, "max": 139.77559888362885, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03057337534160958, "min": 0.028667120692861158, "max": 10.82262453623116, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.6598836547200335, "min": 2.4367052588931983, "max": 173.16199257969856, "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": "1748265723", "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=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics --force", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.7.0+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1748267935" }, "total": 2212.359322229, "count": 1, "self": 0.6500059419995523, "children": { "run_training.setup": { "total": 0.019904646000213688, "count": 1, "self": 0.019904646000213688 }, "TrainerController.start_learning": { "total": 2211.6894116410003, "count": 1, "self": 1.3193430380224527, "children": { "TrainerController._reset_env": { "total": 2.2497440400002233, "count": 1, "self": 2.2497440400002233 }, "TrainerController.advance": { "total": 2207.990215003977, "count": 63959, "self": 1.437296881828388, "children": { "env_step": { "total": 1530.370246138089, "count": 63959, "self": 1378.4640729199996, "children": { "SubprocessEnvManager._take_step": { "total": 151.13844881506293, "count": 63959, "self": 4.670576929028812, "children": { "TorchPolicy.evaluate": { "total": 146.46787188603412, "count": 62561, "self": 146.46787188603412 } } }, "workers": { "total": 0.7677244030264774, "count": 63959, "self": 0.0, "children": { "worker_root": { "total": 2206.749548176067, "count": 63959, "is_parallel": true, "self": 939.5405849380822, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0021188609998716856, "count": 1, "is_parallel": true, "self": 0.0006895959991197742, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014292650007519114, "count": 8, "is_parallel": true, "self": 0.0014292650007519114 } } }, "UnityEnvironment.step": { "total": 0.05124853699999221, "count": 1, "is_parallel": true, "self": 0.0005457679994833597, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005423480001809367, "count": 1, "is_parallel": true, "self": 0.0005423480001809367 }, "communicator.exchange": { "total": 0.04860785800019585, "count": 1, "is_parallel": true, "self": 0.04860785800019585 }, "steps_from_proto": { "total": 0.0015525630001320678, "count": 1, "is_parallel": true, "self": 0.00032939800030362676, "children": { "_process_rank_one_or_two_observation": { "total": 0.001223164999828441, "count": 8, "is_parallel": true, "self": 0.001223164999828441 } } } } } } }, "UnityEnvironment.step": { "total": 1267.2089632379848, "count": 63958, "is_parallel": true, "self": 31.47822235930653, "children": { "UnityEnvironment._generate_step_input": { "total": 23.463053311849308, "count": 63958, "is_parallel": true, "self": 23.463053311849308 }, "communicator.exchange": { "total": 1115.2546183740005, "count": 63958, "is_parallel": true, "self": 1115.2546183740005 }, "steps_from_proto": { "total": 97.01306919282843, "count": 63958, "is_parallel": true, "self": 19.274207613839735, "children": { "_process_rank_one_or_two_observation": { "total": 77.73886157898869, "count": 511664, "is_parallel": true, "self": 77.73886157898869 } } } } } } } } } } }, "trainer_advance": { "total": 676.1826719840597, "count": 63959, "self": 2.5786237721658836, "children": { "process_trajectory": { "total": 132.80550665789042, "count": 63959, "self": 132.55988968489055, "children": { "RLTrainer._checkpoint": { "total": 0.24561697299986918, "count": 2, "self": 0.24561697299986918 } } }, "_update_policy": { "total": 540.7985415540034, "count": 447, "self": 299.38352835700243, "children": { "TorchPPOOptimizer.update": { "total": 241.41501319700092, "count": 22806, "self": 241.41501319700092 } } } } } } }, "trainer_threads": { "total": 1.303999852098059e-06, "count": 1, "self": 1.303999852098059e-06 }, "TrainerController._save_models": { "total": 0.13010825500077772, "count": 1, "self": 0.0016584310005782754, "children": { "RLTrainer._checkpoint": { "total": 0.12844982400019944, "count": 1, "self": 0.12844982400019944 } } } } } } }