{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.360817015171051, "min": 0.360817015171051, "max": 1.4029443264007568, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 10934.19921875, "min": 10934.19921875, "max": 42559.71875, "count": 33 }, "Pyramids.Step.mean": { "value": 989959.0, "min": 29952.0, "max": 989959.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989959.0, "min": 29952.0, "max": 989959.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.3388512134552002, "min": -0.07995842397212982, "max": 0.3388512134552002, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 87.42361450195312, "min": -19.42989730834961, "max": 87.42361450195312, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.02823181450366974, "min": -0.02823181450366974, "max": 0.25994235277175903, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -7.28380823135376, "min": -7.28380823135376, "max": 62.64611053466797, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06673240052690697, "min": 0.06611169342904491, "max": 0.07256744901073449, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9342536073766977, "min": 0.5041180212597962, "max": 1.0621609522232915, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.010467336382277481, "min": 0.0006918364527624996, "max": 0.012717541435426746, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.14654270935188474, "min": 0.009685710338674994, "max": 0.17804558009597443, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.654726019885712e-06, "min": 7.654726019885712e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010716616427839998, "min": 0.00010716616427839998, "max": 0.0036332965889011993, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10255154285714287, "min": 0.10255154285714287, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4357216000000002, "min": 1.3886848, "max": 2.6110988, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002648991314285714, "min": 0.0002648991314285714, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0037085878399999994, "min": 0.0037085878399999994, "max": 0.12112877011999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01236760150641203, "min": 0.01236760150641203, "max": 0.38975873589515686, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.17314642667770386, "min": 0.17314642667770386, "max": 2.728311061859131, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 532.4561403508771, "min": 492.9193548387097, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30350.0, "min": 15984.0, "max": 32970.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.056762039918324, "min": -1.0000000521540642, "max": 1.2751671911263076, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 61.292198315262794, "min": -29.47940167784691, "max": 77.78519865870476, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.056762039918324, "min": -1.0000000521540642, "max": 1.2751671911263076, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 61.292198315262794, "min": -29.47940167784691, "max": 77.78519865870476, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.06905183167766844, "min": 0.0659133618681739, "max": 7.183867774903774, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.0050062373047695, "min": 3.8888883502222598, "max": 114.94188439846039, "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": "1734879424", "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 --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": "1734881899" }, "total": 2474.889646668, "count": 1, "self": 0.48889495299954433, "children": { "run_training.setup": { "total": 0.08867455399990831, "count": 1, "self": 0.08867455399990831 }, "TrainerController.start_learning": { "total": 2474.312077161, "count": 1, "self": 1.9565238740688073, "children": { "TrainerController._reset_env": { "total": 2.843215581000095, "count": 1, "self": 2.843215581000095 }, "TrainerController.advance": { "total": 2469.4149112699315, "count": 63465, "self": 2.1546860858661603, "children": { "env_step": { "total": 1718.6754874770686, "count": 63465, "self": 1525.2280915350295, "children": { "SubprocessEnvManager._take_step": { "total": 192.26105698601805, "count": 63465, "self": 5.8771759330450095, "children": { "TorchPolicy.evaluate": { "total": 186.38388105297304, "count": 62553, "self": 186.38388105297304 } } }, "workers": { "total": 1.186338956021018, "count": 63465, "self": 0.0, "children": { "worker_root": { "total": 2467.751799720007, "count": 63465, "is_parallel": true, "self": 1090.9290930399425, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.003194167000174275, "count": 1, "is_parallel": true, "self": 0.0008831139996345883, "children": { "_process_rank_one_or_two_observation": { "total": 0.0023110530005396868, "count": 8, "is_parallel": true, "self": 0.0023110530005396868 } } }, "UnityEnvironment.step": { "total": 0.06503457799999524, "count": 1, "is_parallel": true, "self": 0.0007847380002203863, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005539799999496609, "count": 1, "is_parallel": true, "self": 0.0005539799999496609 }, "communicator.exchange": { "total": 0.06158284899993305, "count": 1, "is_parallel": true, "self": 0.06158284899993305 }, "steps_from_proto": { "total": 0.00211301099989214, "count": 1, "is_parallel": true, "self": 0.0005253039998933673, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015877069999987725, "count": 8, "is_parallel": true, "self": 0.0015877069999987725 } } } } } } }, "UnityEnvironment.step": { "total": 1376.8227066800646, "count": 63464, "is_parallel": true, "self": 39.611564060075125, "children": { "UnityEnvironment._generate_step_input": { "total": 26.971058846001824, "count": 63464, "is_parallel": true, "self": 26.971058846001824 }, "communicator.exchange": { "total": 1193.0572905390227, "count": 63464, "is_parallel": true, "self": 1193.0572905390227 }, "steps_from_proto": { "total": 117.18279323496495, "count": 63464, "is_parallel": true, "self": 25.345330304050776, "children": { "_process_rank_one_or_two_observation": { "total": 91.83746293091417, "count": 507712, "is_parallel": true, "self": 91.83746293091417 } } } } } } } } } } }, "trainer_advance": { "total": 748.5847377069967, "count": 63465, "self": 3.5052732709941665, "children": { "process_trajectory": { "total": 147.02464193200058, "count": 63465, "self": 146.8043629620006, "children": { "RLTrainer._checkpoint": { "total": 0.2202789699999812, "count": 2, "self": 0.2202789699999812 } } }, "_update_policy": { "total": 598.054822504002, "count": 454, "self": 334.39204836000727, "children": { "TorchPPOOptimizer.update": { "total": 263.66277414399474, "count": 22794, "self": 263.66277414399474 } } } } } } }, "trainer_threads": { "total": 1.0789999578264542e-06, "count": 1, "self": 1.0789999578264542e-06 }, "TrainerController._save_models": { "total": 0.09742535699979271, "count": 1, "self": 0.0016327950002050784, "children": { "RLTrainer._checkpoint": { "total": 0.09579256199958763, "count": 1, "self": 0.09579256199958763 } } } } } } }