{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.40605440735816956, "min": 0.40605440735816956, "max": 1.4675792455673218, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 12233.607421875, "min": 12233.607421875, "max": 44520.484375, "count": 33 }, "Pyramids.Step.mean": { "value": 989991.0, "min": 29952.0, "max": 989991.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989991.0, "min": 29952.0, "max": 989991.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5200446844100952, "min": -0.09241996705532074, "max": 0.5498690009117126, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 144.57241821289062, "min": -22.273212432861328, "max": 152.313720703125, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.0009712621103972197, "min": 0.0006422036676667631, "max": 0.26504847407341003, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 0.2700108587741852, "min": 0.17146837711334229, "max": 63.611637115478516, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06757382870548302, "min": 0.06582893934682944, "max": 0.07321722941972622, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0136074305822453, "min": 0.4965153287928257, "max": 1.0349961996544155, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016081267626981973, "min": 0.0005859016836545584, "max": 0.016648654285485724, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.24121901440472962, "min": 0.0064449185202001425, "max": 0.24121901440472962, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.450297516600001e-06, "min": 7.450297516600001e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011175446274900002, "min": 0.00011175446274900002, "max": 0.0032537981154006994, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10248340000000002, "min": 0.10248340000000002, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5372510000000001, "min": 1.3691136000000002, "max": 2.4423312, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002580916600000001, "min": 0.0002580916600000001, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003871374900000001, "min": 0.003871374900000001, "max": 0.10848147007, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010472399182617664, "min": 0.010472399182617664, "max": 0.37287530303001404, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.15708598494529724, "min": 0.15094611048698425, "max": 2.6101272106170654, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 342.8139534883721, "min": 335.3333333333333, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29482.0, "min": 15984.0, "max": 32883.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.631498807493378, "min": -1.0000000521540642, "max": 1.631498807493378, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 138.67739863693714, "min": -32.000001668930054, "max": 138.67739863693714, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.631498807493378, "min": -1.0000000521540642, "max": 1.631498807493378, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 138.67739863693714, "min": -32.000001668930054, "max": 138.67739863693714, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03765052792082048, "min": 0.03765052792082048, "max": 7.590992618352175, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.2002948732697405, "min": 3.2002948732697405, "max": 121.4558818936348, "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": "1778763589", "python_version": "3.10.12 (main, Mar 3 2026, 11:56:32) [GCC 11.4.0]", "command_line_arguments": "/content/mlagents_env/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=PyramidsTraining --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": "1778766251" }, "total": 2662.9415826580002, "count": 1, "self": 0.7889812470002653, "children": { "run_training.setup": { "total": 0.021422281000013754, "count": 1, "self": 0.021422281000013754 }, "TrainerController.start_learning": { "total": 2662.13117913, "count": 1, "self": 1.669814013002906, "children": { "TrainerController._reset_env": { "total": 2.4172354369998175, "count": 1, "self": 2.4172354369998175 }, "TrainerController.advance": { "total": 2657.9034965919964, "count": 63664, "self": 1.7585518880141535, "children": { "env_step": { "total": 1931.0187695609402, "count": 63664, "self": 1745.0979504719908, "children": { "SubprocessEnvManager._take_step": { "total": 184.91155936700125, "count": 63664, "self": 5.285863884039372, "children": { "TorchPolicy.evaluate": { "total": 179.62569548296187, "count": 62558, "self": 179.62569548296187 } } }, "workers": { "total": 1.0092597219481831, "count": 63664, "self": 0.0, "children": { "worker_root": { "total": 2657.633515961957, "count": 63664, "is_parallel": true, "self": 1040.416748081845, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0020561659998747928, "count": 1, "is_parallel": true, "self": 0.0006514260003314121, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014047399995433807, "count": 8, "is_parallel": true, "self": 0.0014047399995433807 } } }, "UnityEnvironment.step": { "total": 0.08733649500027241, "count": 1, "is_parallel": true, "self": 0.0005030600000281993, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005169920000298589, "count": 1, "is_parallel": true, "self": 0.0005169920000298589 }, "communicator.exchange": { "total": 0.082561442000042, "count": 1, "is_parallel": true, "self": 0.082561442000042 }, "steps_from_proto": { "total": 0.003755001000172342, "count": 1, "is_parallel": true, "self": 0.0003514460004225839, "children": { "_process_rank_one_or_two_observation": { "total": 0.0034035549997497583, "count": 8, "is_parallel": true, "self": 0.0034035549997497583 } } } } } } }, "UnityEnvironment.step": { "total": 1617.216767880112, "count": 63663, "is_parallel": true, "self": 36.092520527151464, "children": { "UnityEnvironment._generate_step_input": { "total": 25.58577518996026, "count": 63663, "is_parallel": true, "self": 25.58577518996026 }, "communicator.exchange": { "total": 1431.0207280230138, "count": 63663, "is_parallel": true, "self": 1431.0207280230138 }, "steps_from_proto": { "total": 124.51774413998646, "count": 63663, "is_parallel": true, "self": 26.93730660122128, "children": { "_process_rank_one_or_two_observation": { "total": 97.58043753876518, "count": 509304, "is_parallel": true, "self": 97.58043753876518 } } } } } } } } } } }, "trainer_advance": { "total": 725.126175143042, "count": 63664, "self": 3.1730599610395984, "children": { "process_trajectory": { "total": 140.74662207000347, "count": 63664, "self": 140.48376740200365, "children": { "RLTrainer._checkpoint": { "total": 0.26285466799981805, "count": 2, "self": 0.26285466799981805 } } }, "_update_policy": { "total": 581.206493111999, "count": 439, "self": 315.4950084850125, "children": { "TorchPPOOptimizer.update": { "total": 265.7114846269865, "count": 22857, "self": 265.7114846269865 } } } } } } }, "trainer_threads": { "total": 1.269000676984433e-06, "count": 1, "self": 1.269000676984433e-06 }, "TrainerController._save_models": { "total": 0.14063181900019117, "count": 1, "self": 0.001443043000108446, "children": { "RLTrainer._checkpoint": { "total": 0.13918877600008273, "count": 1, "self": 0.13918877600008273 } } } } } } }