{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 1.5332887172698975, "min": 1.5332887172698975, "max": 1.5332887172698975, "count": 1 }, "Pyramids.Policy.Entropy.sum": { "value": 46513.84765625, "min": 46513.84765625, "max": 46513.84765625, "count": 1 }, "Pyramids.Step.mean": { "value": 29952.0, "min": 29952.0, "max": 29952.0, "count": 1 }, "Pyramids.Step.sum": { "value": 29952.0, "min": 29952.0, "max": 29952.0, "count": 1 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.0946689024567604, "min": 0.0946689024567604, "max": 0.0946689024567604, "count": 1 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 22.4365291595459, "min": 22.4365291595459, "max": 22.4365291595459, "count": 1 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.1791459023952484, "min": 0.1791459023952484, "max": 0.1791459023952484, "count": 1 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 42.45758056640625, "min": 42.45758056640625, "max": 42.45758056640625, "count": 1 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07402832544897531, "min": 0.07402832544897531, "max": 0.07402832544897531, "count": 1 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.5181982781428272, "min": 0.5181982781428272, "max": 0.5181982781428272, "count": 1 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.012835944597548051, "min": 0.012835944597548051, "max": 0.012835944597548051, "count": 1 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.08985161218283635, "min": 0.08985161218283635, "max": 0.08985161218283635, "count": 1 }, "Pyramids.Policy.LearningRate.mean": { "value": 0.00013835433959619045, "min": 0.00013835433959619045, "max": 0.00013835433959619045, "count": 1 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0009684803771733332, "min": 0.0009684803771733332, "max": 0.0009684803771733332, "count": 1 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1461180952380953, "min": 0.1461180952380953, "max": 0.1461180952380953, "count": 1 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.022826666666667, "min": 1.022826666666667, "max": 1.022826666666667, "count": 1 }, "Pyramids.Policy.Beta.mean": { "value": 0.004617197714285715, "min": 0.004617197714285715, "max": 0.004617197714285715, "count": 1 }, "Pyramids.Policy.Beta.sum": { "value": 0.032320384, "min": 0.032320384, "max": 0.032320384, "count": 1 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.48142391443252563, "min": 0.48142391443252563, "max": 0.48142391443252563, "count": 1 }, "Pyramids.Losses.RNDLoss.sum": { "value": 3.369967460632324, "min": 3.369967460632324, "max": 3.369967460632324, "count": 1 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 999.0, "min": 999.0, "max": 999.0, "count": 1 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 15984.0, "min": 15984.0, "max": 15984.0, "count": 1 }, "Pyramids.Environment.CumulativeReward.mean": { "value": -1.0000000521540642, "min": -1.0000000521540642, "max": -1.0000000521540642, "count": 1 }, "Pyramids.Environment.CumulativeReward.sum": { "value": -16.000000834465027, "min": -16.000000834465027, "max": -16.000000834465027, "count": 1 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": -1.0000000521540642, "min": -1.0000000521540642, "max": -1.0000000521540642, "count": 1 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": -16.000000834465027, "min": -16.000000834465027, "max": -16.000000834465027, "count": 1 }, "Pyramids.Policy.RndReward.mean": { "value": 9.88133719470352, "min": 9.88133719470352, "max": 9.88133719470352, "count": 1 }, "Pyramids.Policy.RndReward.sum": { "value": 158.1013951152563, "min": 158.1013951152563, "max": 158.1013951152563, "count": 1 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1793657852", "python_version": "3.10.22 (main, Oct 9 2026, 15:21:30) [Clang 22.1.3 ]", "command_line_arguments": "/content/venv/bin/mlagents-learn config/ppo/PyramidsRND.yaml --env=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": "1793657917" }, "total": 65.066499411, "count": 1, "self": 0.48197740600005545, "children": { "run_training.setup": { "total": 0.020097474999943188, "count": 1, "self": 0.020097474999943188 }, "TrainerController.start_learning": { "total": 64.56442453, "count": 1, "self": 0.045376352000971565, "children": { "TrainerController._reset_env": { "total": 2.232030602000009, "count": 1, "self": 2.232030602000009 }, "TrainerController.advance": { "total": 62.17902634899906, "count": 1896, "self": 0.04736545099945033, "children": { "env_step": { "total": 43.690408739001214, "count": 1896, "self": 38.56901272800087, "children": { "SubprocessEnvManager._take_step": { "total": 5.095491838003113, "count": 1896, "self": 0.15285785600190138, "children": { "TorchPolicy.evaluate": { "total": 4.942633982001212, "count": 1896, "self": 4.942633982001212 } } }, "workers": { "total": 0.02590417299722958, "count": 1896, "self": 0.0, "children": { "worker_root": { "total": 64.10495337800126, "count": 1896, "is_parallel": true, "self": 29.520680213000787, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0020644539999921108, "count": 1, "is_parallel": true, "self": 0.00065489099995375, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014095630000383608, "count": 8, "is_parallel": true, "self": 0.0014095630000383608 } } }, "UnityEnvironment.step": { "total": 0.05928586599998198, "count": 1, "is_parallel": true, "self": 0.0006368170000996543, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005632959999957166, "count": 1, "is_parallel": true, "self": 0.0005632959999957166 }, "communicator.exchange": { "total": 0.05606173499995748, "count": 1, "is_parallel": true, "self": 0.05606173499995748 }, "steps_from_proto": { "total": 0.0020240179999291286, "count": 1, "is_parallel": true, "self": 0.00045639499990102195, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015676230000281066, "count": 8, "is_parallel": true, "self": 0.0015676230000281066 } } } } } } }, "UnityEnvironment.step": { "total": 34.58427316500047, "count": 1895, "is_parallel": true, "self": 1.0702440519946776, "children": { "UnityEnvironment._generate_step_input": { "total": 0.7233210710013509, "count": 1895, "is_parallel": true, "self": 0.7233210710013509 }, "communicator.exchange": { "total": 29.158811873002264, "count": 1895, "is_parallel": true, "self": 29.158811873002264 }, "steps_from_proto": { "total": 3.631896169002175, "count": 1895, "is_parallel": true, "self": 0.8131902280073291, "children": { "_process_rank_one_or_two_observation": { "total": 2.818705940994846, "count": 15160, "is_parallel": true, "self": 2.818705940994846 } } } } } } } } } } }, "trainer_advance": { "total": 18.441252158998395, "count": 1896, "self": 0.05746138599386086, "children": { "process_trajectory": { "total": 3.405408401004479, "count": 1896, "self": 3.405408401004479 }, "_update_policy": { "total": 14.978382372000056, "count": 7, "self": 7.916644579998888, "children": { "TorchPPOOptimizer.update": { "total": 7.061737792001168, "count": 663, "self": 7.061737792001168 } } } } } } }, "trainer_threads": { "total": 1.0109999948326731e-06, "count": 1, "self": 1.0109999948326731e-06 }, "TrainerController._save_models": { "total": 0.10799021599996195, "count": 1, "self": 0.0009535379999761062, "children": { "RLTrainer._checkpoint": { "total": 0.10703667799998584, "count": 1, "self": 0.10703667799998584 } } } } } } }