{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.47772684693336487, "min": 0.47772684693336487, "max": 1.3927727937698364, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 14362.3798828125, "min": 14362.3798828125, "max": 42251.15625, "count": 33 }, "Pyramids.Step.mean": { "value": 989948.0, "min": 29952.0, "max": 989948.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989948.0, "min": 29952.0, "max": 989948.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.4300295412540436, "min": -0.11631271243095398, "max": 0.5051272511482239, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 116.53800964355469, "min": -28.03136444091797, "max": 137.3946075439453, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.00393707724288106, "min": -0.01222381554543972, "max": 0.37052974104881287, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -1.0669479370117188, "min": -3.165968179702759, "max": 89.29766845703125, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06439430168220063, "min": 0.06312749790196817, "max": 0.07515998430878316, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9015202235508089, "min": 0.5261198901614822, "max": 1.052140429806576, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01458588256666969, "min": 0.00025143508545851515, "max": 0.018389523955106377, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.20420235593337566, "min": 0.0027657859400436664, "max": 0.25789407869888237, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.717597427499999e-06, "min": 7.717597427499999e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010804636398499999, "min": 0.00010804636398499999, "max": 0.0031372484542506003, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10257250000000002, "min": 0.10257250000000002, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4360150000000003, "min": 1.3886848, "max": 2.4015641, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026699275000000006, "min": 0.00026699275000000006, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0037378985000000005, "min": 0.0037378985000000005, "max": 0.10460036506000002, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01262518297880888, "min": 0.01262518297880888, "max": 0.5381245017051697, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.17675256729125977, "min": 0.17675256729125977, "max": 3.766871690750122, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 439.72857142857146, "min": 391.35135135135135, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30781.0, "min": 15984.0, "max": 32714.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.3887914008327893, "min": -1.0000000521540642, "max": 1.511192755885871, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 97.21539805829525, "min": -31.998001664876938, "max": 125.4289987385273, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.3887914008327893, "min": -1.0000000521540642, "max": 1.511192755885871, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 97.21539805829525, "min": -31.998001664876938, "max": 125.4289987385273, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.057534807836470594, "min": 0.05293053589412011, "max": 10.797408495098352, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.0274365485529415, "min": 3.9631085150904255, "max": 172.75853592157364, "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": "1752792531", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "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": "2.7.1+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1752794953" }, "total": 2422.0379652009997, "count": 1, "self": 0.5419398960002582, "children": { "run_training.setup": { "total": 0.02296379099971091, "count": 1, "self": 0.02296379099971091 }, "TrainerController.start_learning": { "total": 2421.4730615139997, "count": 1, "self": 1.7118972439457139, "children": { "TrainerController._reset_env": { "total": 2.4048433239995575, "count": 1, "self": 2.4048433239995575 }, "TrainerController.advance": { "total": 2417.271329973054, "count": 63593, "self": 1.8458902741213024, "children": { "env_step": { "total": 1702.8830783990206, "count": 63593, "self": 1524.1484401592888, "children": { "SubprocessEnvManager._take_step": { "total": 177.67161854071037, "count": 63593, "self": 5.2646009166373915, "children": { "TorchPolicy.evaluate": { "total": 172.40701762407298, "count": 62561, "self": 172.40701762407298 } } }, "workers": { "total": 1.0630196990214245, "count": 63593, "self": 0.0, "children": { "worker_root": { "total": 2414.9033675449036, "count": 63593, "is_parallel": true, "self": 1023.8340422779302, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0019505250002112007, "count": 1, "is_parallel": true, "self": 0.0006774880012017093, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012730369990094914, "count": 8, "is_parallel": true, "self": 0.0012730369990094914 } } }, "UnityEnvironment.step": { "total": 0.10919255099997827, "count": 1, "is_parallel": true, "self": 0.0005851079995409236, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00043934699988312786, "count": 1, "is_parallel": true, "self": 0.00043934699988312786 }, "communicator.exchange": { "total": 0.10664585500035173, "count": 1, "is_parallel": true, "self": 0.10664585500035173 }, "steps_from_proto": { "total": 0.0015222410002024844, "count": 1, "is_parallel": true, "self": 0.00032817900137160905, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011940619988308754, "count": 8, "is_parallel": true, "self": 0.0011940619988308754 } } } } } } }, "UnityEnvironment.step": { "total": 1391.0693252669735, "count": 63592, "is_parallel": true, "self": 36.027238205740105, "children": { "UnityEnvironment._generate_step_input": { "total": 24.464527751027163, "count": 63592, "is_parallel": true, "self": 24.464527751027163 }, "communicator.exchange": { "total": 1225.4269445670807, "count": 63592, "is_parallel": true, "self": 1225.4269445670807 }, "steps_from_proto": { "total": 105.15061474312552, "count": 63592, "is_parallel": true, "self": 21.850989009141813, "children": { "_process_rank_one_or_two_observation": { "total": 83.2996257339837, "count": 508736, "is_parallel": true, "self": 83.2996257339837 } } } } } } } } } } }, "trainer_advance": { "total": 712.542361299912, "count": 63593, "self": 3.2456132081188116, "children": { "process_trajectory": { "total": 135.15215531279955, "count": 63593, "self": 134.90456505279963, "children": { "RLTrainer._checkpoint": { "total": 0.24759025999992446, "count": 2, "self": 0.24759025999992446 } } }, "_update_policy": { "total": 574.1445927789937, "count": 444, "self": 320.03118341802656, "children": { "TorchPPOOptimizer.update": { "total": 254.11340936096713, "count": 22821, "self": 254.11340936096713 } } } } } } }, "trainer_threads": { "total": 1.0720004866016097e-06, "count": 1, "self": 1.0720004866016097e-06 }, "TrainerController._save_models": { "total": 0.08498990099997172, "count": 1, "self": 0.0013426630002868478, "children": { "RLTrainer._checkpoint": { "total": 0.08364723799968488, "count": 1, "self": 0.08364723799968488 } } } } } } }