{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.524682343006134, "min": 0.5242065191268921, "max": 1.4393885135650635, "count": 35 }, "Pyramids.Policy.Entropy.sum": { "value": 15816.025390625, "min": 15801.681640625, "max": 43665.2890625, "count": 35 }, "Pyramids.Step.mean": { "value": 1049986.0, "min": 29952.0, "max": 1049986.0, "count": 35 }, "Pyramids.Step.sum": { "value": 1049986.0, "min": 29952.0, "max": 1049986.0, "count": 35 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.2385096251964569, "min": -0.09352134168148041, "max": 0.343773752450943, "count": 35 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 60.81995391845703, "min": -22.53864288330078, "max": 87.66230773925781, "count": 35 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.012406859546899796, "min": -0.018919428810477257, "max": 0.265118807554245, "count": 35 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.1637492179870605, "min": -4.748776435852051, "max": 62.833160400390625, "count": 35 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06999519658746153, "min": 0.06497630802788569, "max": 0.07428414650244772, "count": 35 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9799327522244615, "min": 0.5174236427427232, "max": 1.0608741467745573, "count": 35 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.010662162796680127, "min": 0.0002656494752834231, "max": 0.014327028206545427, "count": 35 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.14927027915352178, "min": 0.002922144228117654, "max": 0.2095450727486191, "count": 35 }, "Pyramids.Policy.LearningRate.mean": { "value": 0.00019656148447951666, "min": 0.00019656148447951666, "max": 0.00029838354339596195, "count": 35 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0027518607827132333, "min": 0.0020886848037717336, "max": 0.0038428685190438666, "count": 35 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.16552048333333333, "min": 0.16552048333333333, "max": 0.19946118095238097, "count": 35 }, "Pyramids.Policy.Epsilon.sum": { "value": 2.3172867666666668, "min": 1.3962282666666668, "max": 2.7375373666666665, "count": 35 }, "Pyramids.Policy.Beta.mean": { "value": 0.006555496285000001, "min": 0.006555496285000001, "max": 0.009946171977142856, "count": 35 }, "Pyramids.Policy.Beta.sum": { "value": 0.09177694799000001, "min": 0.06962320384, "max": 0.12810751772, "count": 35 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.0036689122207462788, "min": 0.0036689122207462788, "max": 0.330904483795166, "count": 35 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.05136477202177048, "min": 0.05136477202177048, "max": 2.316331386566162, "count": 35 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 641.4347826086956, "min": 523.0535714285714, "max": 999.0, "count": 35 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29506.0, "min": 15984.0, "max": 34789.0, "count": 35 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.7931304010360137, "min": -1.0000000521540642, "max": 1.267356339097023, "count": 35 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 36.48399844765663, "min": -31.996801644563675, "max": 69.70459865033627, "count": 35 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.7931304010360137, "min": -1.0000000521540642, "max": 1.267356339097023, "count": 35 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 36.48399844765663, "min": -31.996801644563675, "max": 69.70459865033627, "count": 35 }, "Pyramids.Policy.RndReward.mean": { "value": 0.024475672705707635, "min": 0.021987935857826168, "max": 6.924512376077473, "count": 35 }, "Pyramids.Policy.RndReward.sum": { "value": 1.1258809444625513, "min": 1.1258809444625513, "max": 110.79219801723957, "count": 35 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 35 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 35 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1736112511", "python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids_Training_01 --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": "1736114800" }, "total": 2288.4478331890004, "count": 1, "self": 0.335839842000496, "children": { "run_training.setup": { "total": 0.0552270129999215, "count": 1, "self": 0.0552270129999215 }, "TrainerController.start_learning": { "total": 2288.056766334, "count": 1, "self": 1.3041458880120445, "children": { "TrainerController._reset_env": { "total": 5.889830845999995, "count": 1, "self": 5.889830845999995 }, "TrainerController.advance": { "total": 2280.7190817129876, "count": 66988, "self": 1.3722035790324298, "children": { "env_step": { "total": 1555.8245483229757, "count": 66988, "self": 1404.2284571230218, "children": { "SubprocessEnvManager._take_step": { "total": 150.81076787499637, "count": 66988, "self": 4.612636135962248, "children": { "TorchPolicy.evaluate": { "total": 146.19813173903412, "count": 66069, "self": 146.19813173903412 } } }, "workers": { "total": 0.7853233249575169, "count": 66987, "self": 0.0, "children": { "worker_root": { "total": 2282.977967810012, "count": 66987, "is_parallel": true, "self": 995.0547126629974, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0020403879998411867, "count": 1, "is_parallel": true, "self": 0.0007084019996455027, "children": { "_process_rank_one_or_two_observation": { "total": 0.001331986000195684, "count": 8, "is_parallel": true, "self": 0.001331986000195684 } } }, "UnityEnvironment.step": { "total": 0.06299638999985291, "count": 1, "is_parallel": true, "self": 0.0006847429999652377, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004950919999373582, "count": 1, "is_parallel": true, "self": 0.0004950919999373582 }, "communicator.exchange": { "total": 0.060071354999990945, "count": 1, "is_parallel": true, "self": 0.060071354999990945 }, "steps_from_proto": { "total": 0.0017451999999593681, "count": 1, "is_parallel": true, "self": 0.0004244679996645573, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013207320002948109, "count": 8, "is_parallel": true, "self": 0.0013207320002948109 } } } } } } }, "UnityEnvironment.step": { "total": 1287.9232551470147, "count": 66986, "is_parallel": true, "self": 34.163634766957784, "children": { "UnityEnvironment._generate_step_input": { "total": 24.25692494500072, "count": 66986, "is_parallel": true, "self": 24.25692494500072 }, "communicator.exchange": { "total": 1129.4816217360699, "count": 66986, "is_parallel": true, "self": 1129.4816217360699 }, "steps_from_proto": { "total": 100.02107369898636, "count": 66986, "is_parallel": true, "self": 19.86935684197215, "children": { "_process_rank_one_or_two_observation": { "total": 80.15171685701421, "count": 535888, "is_parallel": true, "self": 80.15171685701421 } } } } } } } } } } }, "trainer_advance": { "total": 723.5223298109795, "count": 66987, "self": 2.448586852940025, "children": { "process_trajectory": { "total": 137.6810954370353, "count": 66987, "self": 137.43599303703513, "children": { "RLTrainer._checkpoint": { "total": 0.24510240000017802, "count": 2, "self": 0.24510240000017802 } } }, "_update_policy": { "total": 583.3926475210042, "count": 472, "self": 329.3002591560289, "children": { "TorchPPOOptimizer.update": { "total": 254.09238836497525, "count": 24072, "self": 254.09238836497525 } } } } } } }, "trainer_threads": { "total": 1.4289998944150284e-06, "count": 1, "self": 1.4289998944150284e-06 }, "TrainerController._save_models": { "total": 0.14370645799999693, "count": 1, "self": 0.002043453000169393, "children": { "RLTrainer._checkpoint": { "total": 0.14166300499982754, "count": 1, "self": 0.14166300499982754 } } } } } } }