{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.35658976435661316, "min": 0.3331056833267212, "max": 1.4760292768478394, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 10674.87109375, "min": 9923.884765625, "max": 44776.82421875, "count": 33 }, "Pyramids.Step.mean": { "value": 989914.0, "min": 29952.0, "max": 989914.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989914.0, "min": 29952.0, "max": 989914.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6154794692993164, "min": -0.11654443293809891, "max": 0.6294873952865601, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 174.18069458007812, "min": -28.087207794189453, "max": 180.0334014892578, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.013437376357614994, "min": 0.01027122512459755, "max": 0.3159535229206085, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.8027775287628174, "min": 2.6955134868621826, "max": 74.8809814453125, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07418094402868683, "min": 0.06512957207589698, "max": 0.07418094402868683, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0385332164016157, "min": 0.5133089425803989, "max": 1.0733813048185161, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01601655823207847, "min": 0.0009851681324070558, "max": 0.017760422835009126, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.22423181524909858, "min": 0.011822017588884669, "max": 0.25562469585851183, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.519404636421428e-06, "min": 7.519404636421428e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001052716649099, "min": 0.0001052716649099, "max": 0.0036319810893397, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10250643571428572, "min": 0.10250643571428572, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4350901, "min": 1.3886848, "max": 2.6106603, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002603929278571428, "min": 0.0002603929278571428, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036455009899999994, "min": 0.0036455009899999994, "max": 0.12108496397000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.011638781055808067, "min": 0.011638781055808067, "max": 0.4080459177494049, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.16294293105602264, "min": 0.16294293105602264, "max": 2.856321334838867, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 306.21875, "min": 289.0, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29397.0, "min": 15984.0, "max": 33124.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6521104016962151, "min": -1.0000000521540642, "max": 1.710446584427241, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 158.60259856283665, "min": -30.701001688838005, "max": 176.17599819600582, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6521104016962151, "min": -1.0000000521540642, "max": 1.710446584427241, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 158.60259856283665, "min": -30.701001688838005, "max": 176.17599819600582, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03657354053696812, "min": 0.03657354053696812, "max": 7.9046113146469, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.511059891548939, "min": 3.511059891548939, "max": 126.4737810343504, "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": "1745696676", "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": "2.7.0+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1745700113" }, "total": 3436.478315708, "count": 1, "self": 1.6112244320001992, "children": { "run_training.setup": { "total": 0.05221841900004165, "count": 1, "self": 0.05221841900004165 }, "TrainerController.start_learning": { "total": 3434.814872857, "count": 1, "self": 2.4369127389882124, "children": { "TrainerController._reset_env": { "total": 5.752178758000014, "count": 1, "self": 5.752178758000014 }, "TrainerController.advance": { "total": 3426.537252117012, "count": 63906, "self": 2.6587248489777267, "children": { "env_step": { "total": 2298.2334884769466, "count": 63906, "self": 2126.5005055660195, "children": { "SubprocessEnvManager._take_step": { "total": 170.31154498091064, "count": 63906, "self": 7.335669818887936, "children": { "TorchPolicy.evaluate": { "total": 162.9758751620227, "count": 62554, "self": 162.9758751620227 } } }, "workers": { "total": 1.4214379300165092, "count": 63906, "self": 0.0, "children": { "worker_root": { "total": 3426.818158241989, "count": 63906, "is_parallel": true, "self": 1483.0403354300224, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.008046550000017305, "count": 1, "is_parallel": true, "self": 0.0053576230002363445, "children": { "_process_rank_one_or_two_observation": { "total": 0.0026889269997809606, "count": 8, "is_parallel": true, "self": 0.0026889269997809606 } } }, "UnityEnvironment.step": { "total": 0.06593429800000195, "count": 1, "is_parallel": true, "self": 0.0007042770000680321, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005480569999463114, "count": 1, "is_parallel": true, "self": 0.0005480569999463114 }, "communicator.exchange": { "total": 0.06260096400001203, "count": 1, "is_parallel": true, "self": 0.06260096400001203 }, "steps_from_proto": { "total": 0.0020809999999755746, "count": 1, "is_parallel": true, "self": 0.0006046210000931751, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014763789998823995, "count": 8, "is_parallel": true, "self": 0.0014763789998823995 } } } } } } }, "UnityEnvironment.step": { "total": 1943.7778228119664, "count": 63905, "is_parallel": true, "self": 47.44959465695911, "children": { "UnityEnvironment._generate_step_input": { "total": 31.589715558062494, "count": 63905, "is_parallel": true, "self": 31.589715558062494 }, "communicator.exchange": { "total": 1736.240619419968, "count": 63905, "is_parallel": true, "self": 1736.240619419968 }, "steps_from_proto": { "total": 128.49789317697707, "count": 63905, "is_parallel": true, "self": 27.821514773989065, "children": { "_process_rank_one_or_two_observation": { "total": 100.67637840298801, "count": 511240, "is_parallel": true, "self": 100.67637840298801 } } } } } } } } } } }, "trainer_advance": { "total": 1125.645038791088, "count": 63906, "self": 4.8401443330815255, "children": { "process_trajectory": { "total": 171.0390217900084, "count": 63906, "self": 170.45583221500863, "children": { "RLTrainer._checkpoint": { "total": 0.5831895749997784, "count": 2, "self": 0.5831895749997784 } } }, "_update_policy": { "total": 949.7658726679981, "count": 450, "self": 373.88879777101056, "children": { "TorchPPOOptimizer.update": { "total": 575.8770748969876, "count": 22815, "self": 575.8770748969876 } } } } } } }, "trainer_threads": { "total": 9.469999895372894e-07, "count": 1, "self": 9.469999895372894e-07 }, "TrainerController._save_models": { "total": 0.08852829599982215, "count": 1, "self": 0.0020529459998215316, "children": { "RLTrainer._checkpoint": { "total": 0.08647535000000062, "count": 1, "self": 0.08647535000000062 } } } } } } }