{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 1.1326735019683838, "min": 1.1326735019683838, "max": 1.4304245710372925, "count": 2 }, "Pyramids.Policy.Entropy.sum": { "value": 33925.8359375, "min": 33925.8359375, "max": 43393.359375, "count": 2 }, "Pyramids.Step.mean": { "value": 59946.0, "min": 29952.0, "max": 59946.0, "count": 2 }, "Pyramids.Step.sum": { "value": 59946.0, "min": 29952.0, "max": 59946.0, "count": 2 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": -0.04576873406767845, "min": -0.04576873406767845, "max": 0.10741014778614044, "count": 2 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": -11.030264854431152, "min": -11.030264854431152, "max": 25.456205368041992, "count": 2 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.28123435378074646, "min": 0.22929435968399048, "max": 0.28123435378074646, "count": 2 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 67.77748107910156, "min": 54.3427619934082, "max": 67.77748107910156, "count": 2 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06733730155226172, "min": 0.06733730155226172, "max": 0.0696023349759021, "count": 2 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.6060357139703555, "min": 0.48721634483131465, "max": 0.6060357139703555, "count": 2 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.0015927756046879718, "min": 0.0015927756046879718, "max": 0.008589118875408593, "count": 2 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.014334980442191747, "min": 0.014334980442191747, "max": 0.06012383212786015, "count": 2 }, "Pyramids.Policy.LearningRate.mean": { "value": 0.0002955432237078148, "min": 0.0002955432237078148, "max": 0.00029838354339596195, "count": 2 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0026598890133703334, "min": 0.0020886848037717336, "max": 0.0026598890133703334, "count": 2 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.19851440740740742, "min": 0.19851440740740742, "max": 0.19946118095238097, "count": 2 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.7866296666666668, "min": 1.3962282666666668, "max": 1.7866296666666668, "count": 2 }, "Pyramids.Policy.Beta.mean": { "value": 0.0098515893, "min": 0.0098515893, "max": 0.009946171977142856, "count": 2 }, "Pyramids.Policy.Beta.sum": { "value": 0.0886643037, "min": 0.06962320384, "max": 0.0886643037, "count": 2 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.15621216595172882, "min": 0.15621216595172882, "max": 0.5564442276954651, "count": 2 }, "Pyramids.Losses.RNDLoss.sum": { "value": 1.405909538269043, "min": 1.405909538269043, "max": 3.8951096534729004, "count": 2 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 977.7272727272727, "min": 977.7272727272727, "max": 999.0, "count": 2 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 32265.0, "min": 15984.0, "max": 32265.0, "count": 2 }, "Pyramids.Environment.CumulativeReward.mean": { "value": -0.9180848998102275, "min": -1.0000000521540642, "max": -0.9180848998102275, "count": 2 }, "Pyramids.Environment.CumulativeReward.sum": { "value": -30.296801693737507, "min": -30.296801693737507, "max": -16.000000834465027, "count": 2 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": -0.9180848998102275, "min": -1.0000000521540642, "max": -0.9180848998102275, "count": 2 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": -30.296801693737507, "min": -30.296801693737507, "max": -16.000000834465027, "count": 2 }, "Pyramids.Policy.RndReward.mean": { "value": 2.3573899833541927, "min": 2.3573899833541927, "max": 11.591242898255587, "count": 2 }, "Pyramids.Policy.RndReward.sum": { "value": 77.79386945068836, "min": 77.79386945068836, "max": 185.4598863720894, "count": 2 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 2 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 2 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1788952853", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/usr/local/envs/mlagents_env/bin/mlagents-learn ./ml-agents/config/ppo/PyramidsRND.yaml --env=./ml-agents/training-envs-executables/linux/Pyramids/Pyramids.x86_64 --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": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1788953025" }, "total": 171.57627388299989, "count": 1, "self": 0.4271281889996317, "children": { "run_training.setup": { "total": 0.019777153999712027, "count": 1, "self": 0.019777153999712027 }, "TrainerController.start_learning": { "total": 171.12936854000054, "count": 1, "self": 0.10190857096949912, "children": { "TrainerController._reset_env": { "total": 2.1498928829996657, "count": 1, "self": 2.1498928829996657 }, "TrainerController.advance": { "total": 168.87431218203074, "count": 5108, "self": 0.11010478208118002, "children": { "env_step": { "total": 116.15775260995997, "count": 5108, "self": 103.40725639992161, "children": { "SubprocessEnvManager._take_step": { "total": 12.685953615027756, "count": 5108, "self": 0.3773428870135831, "children": { "TorchPolicy.evaluate": { "total": 12.308610728014173, "count": 5103, "self": 12.308610728014173 } } }, "workers": { "total": 0.06454259501060733, "count": 5107, "self": 0.0, "children": { "worker_root": { "total": 170.75613260405134, "count": 5107, "is_parallel": true, "self": 76.94637303403852, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0019172610000168788, "count": 1, "is_parallel": true, "self": 0.0006624840016229427, "children": { "_process_rank_one_or_two_observation": { "total": 0.001254776998393936, "count": 8, "is_parallel": true, "self": 0.001254776998393936 } } }, "UnityEnvironment.step": { "total": 0.052737856000021566, "count": 1, "is_parallel": true, "self": 0.0005768709997937549, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000507067999933497, "count": 1, "is_parallel": true, "self": 0.000507067999933497 }, "communicator.exchange": { "total": 0.049888366000232054, "count": 1, "is_parallel": true, "self": 0.049888366000232054 }, "steps_from_proto": { "total": 0.0017655510000622598, "count": 1, "is_parallel": true, "self": 0.00038669199966534507, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013788590003969148, "count": 8, "is_parallel": true, "self": 0.0013788590003969148 } } } } } } }, "UnityEnvironment.step": { "total": 93.80975957001283, "count": 5106, "is_parallel": true, "self": 2.763928715039583, "children": { "UnityEnvironment._generate_step_input": { "total": 1.9477532849496129, "count": 5106, "is_parallel": true, "self": 1.9477532849496129 }, "communicator.exchange": { "total": 80.30278011201608, "count": 5106, "is_parallel": true, "self": 80.30278011201608 }, "steps_from_proto": { "total": 8.795297458007553, "count": 5106, "is_parallel": true, "self": 1.8324940280799638, "children": { "_process_rank_one_or_two_observation": { "total": 6.96280342992759, "count": 40848, "is_parallel": true, "self": 6.96280342992759 } } } } } } } } } } }, "trainer_advance": { "total": 52.606454789989584, "count": 5107, "self": 0.13316747795397532, "children": { "process_trajectory": { "total": 8.295960873037075, "count": 5107, "self": 8.295960873037075 }, "_update_policy": { "total": 44.177326438998534, "count": 24, "self": 24.167713988998003, "children": { "TorchPPOOptimizer.update": { "total": 20.00961245000053, "count": 1827, "self": 20.00961245000053 } } } } } } }, "trainer_threads": { "total": 1.4430006558541209e-06, "count": 1, "self": 1.4430006558541209e-06 }, "TrainerController._save_models": { "total": 0.003253460999985691, "count": 1, "self": 2.27230002565193e-05, "children": { "RLTrainer._checkpoint": { "total": 0.003230737999729172, "count": 1, "self": 0.003230737999729172 } } } } } } }