{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4868679642677307, "min": 0.4566994607448578, "max": 1.5162100791931152, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 14458.03125, "min": 13744.8271484375, "max": 45995.75, "count": 33 }, "Pyramids.Step.mean": { "value": 989934.0, "min": 29952.0, "max": 989934.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989934.0, "min": 29952.0, "max": 989934.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5779014229774475, "min": -0.2761842608451843, "max": 0.6295759677886963, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 161.2344970703125, "min": -65.45567321777344, "max": 175.02212524414062, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.002665495965629816, "min": -0.018158789724111557, "max": 0.23072706162929535, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -0.7436733841896057, "min": -5.066302299499512, "max": 55.37449645996094, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06812668722566394, "min": 0.06516291518217057, "max": 0.07402020464983902, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9537736211592952, "min": 0.4876467390961065, "max": 1.0581046191897863, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01404777362560188, "min": 0.0006330671059822772, "max": 0.015961097399537848, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.19666883075842634, "min": 0.005204667436094068, "max": 0.22345536359352988, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.67129030007857e-06, "min": 7.67129030007857e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010739806420109998, "min": 0.00010739806420109998, "max": 0.0032546030151323997, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1025570642857143, "min": 0.1025570642857143, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4357989000000002, "min": 1.3691136000000002, "max": 2.4018411, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026545072214285704, "min": 0.00026545072214285704, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0037163101099999987, "min": 0.0037163101099999987, "max": 0.10850827324, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.00764014245942235, "min": 0.00749075785279274, "max": 0.3766403794288635, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.10696199536323547, "min": 0.10487060993909836, "max": 2.6364827156066895, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 338.78409090909093, "min": 304.4782608695652, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29813.0, "min": 15984.0, "max": 33074.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.638481798327782, "min": -1.0000000521540642, "max": 1.673773896597002, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 144.1863982528448, "min": -32.000001668930054, "max": 154.07339801639318, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.638481798327782, "min": -1.0000000521540642, "max": 1.673773896597002, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 144.1863982528448, "min": -32.000001668930054, "max": 154.07339801639318, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.026904295099732488, "min": 0.02480038805638048, "max": 7.568391473963857, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.367577968776459, "min": 2.3492030715569854, "max": 121.09426358342171, "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": "1793119123", "python_version": "3.10.22 (main, Oct 1 2026, 15:39:47) [GCC 13.3.0]", "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": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1793121178" }, "total": 2055.958595792, "count": 1, "self": 0.4786943849999261, "children": { "run_training.setup": { "total": 0.02087846399990667, "count": 1, "self": 0.02087846399990667 }, "TrainerController.start_learning": { "total": 2055.459022943, "count": 1, "self": 1.3415919970734649, "children": { "TrainerController._reset_env": { "total": 2.22822032199997, "count": 1, "self": 2.22822032199997 }, "TrainerController.advance": { "total": 2051.8181294609267, "count": 63948, "self": 1.4117817459446087, "children": { "env_step": { "total": 1445.7947908319636, "count": 63948, "self": 1296.7578218759106, "children": { "SubprocessEnvManager._take_step": { "total": 148.22314928398646, "count": 63948, "self": 4.529302374014833, "children": { "TorchPolicy.evaluate": { "total": 143.69384690997163, "count": 62568, "self": 143.69384690997163 } } }, "workers": { "total": 0.8138196720665292, "count": 63948, "self": 0.0, "children": { "worker_root": { "total": 2052.036498641032, "count": 63948, "is_parallel": true, "self": 861.3719016529974, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018589789999623463, "count": 1, "is_parallel": true, "self": 0.0006643320000421227, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011946469999202236, "count": 8, "is_parallel": true, "self": 0.0011946469999202236 } } }, "UnityEnvironment.step": { "total": 0.05075837999993382, "count": 1, "is_parallel": true, "self": 0.0005885619998480252, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004224840001825214, "count": 1, "is_parallel": true, "self": 0.0004224840001825214 }, "communicator.exchange": { "total": 0.047784726999907434, "count": 1, "is_parallel": true, "self": 0.047784726999907434 }, "steps_from_proto": { "total": 0.0019626069999958418, "count": 1, "is_parallel": true, "self": 0.0004102309999325371, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015523760000633047, "count": 8, "is_parallel": true, "self": 0.0015523760000633047 } } } } } } }, "UnityEnvironment.step": { "total": 1190.6645969880344, "count": 63947, "is_parallel": true, "self": 32.39863373193771, "children": { "UnityEnvironment._generate_step_input": { "total": 22.87580661002994, "count": 63947, "is_parallel": true, "self": 22.87580661002994 }, "communicator.exchange": { "total": 1034.1681654990393, "count": 63947, "is_parallel": true, "self": 1034.1681654990393 }, "steps_from_proto": { "total": 101.22199114702744, "count": 63947, "is_parallel": true, "self": 20.49988650588648, "children": { "_process_rank_one_or_two_observation": { "total": 80.72210464114096, "count": 511576, "is_parallel": true, "self": 80.72210464114096 } } } } } } } } } } }, "trainer_advance": { "total": 604.6115568830185, "count": 63948, "self": 2.431134301052225, "children": { "process_trajectory": { "total": 109.59619152596315, "count": 63948, "self": 109.40615940296311, "children": { "RLTrainer._checkpoint": { "total": 0.19003212300003725, "count": 2, "self": 0.19003212300003725 } } }, "_update_policy": { "total": 492.5842310560031, "count": 439, "self": 260.337732082985, "children": { "TorchPPOOptimizer.update": { "total": 232.2464989730181, "count": 22818, "self": 232.2464989730181 } } } } } } }, "trainer_threads": { "total": 8.789997991698328e-07, "count": 1, "self": 8.789997991698328e-07 }, "TrainerController._save_models": { "total": 0.07108028399989053, "count": 1, "self": 0.0009711749999041785, "children": { "RLTrainer._checkpoint": { "total": 0.07010910899998635, "count": 1, "self": 0.07010910899998635 } } } } } } }