{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5225072503089905, "min": 0.5225072503089905, "max": 1.4866514205932617, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 15742.0986328125, "min": 15742.0986328125, "max": 45099.05859375, "count": 33 }, "Pyramids.Step.mean": { "value": 989928.0, "min": 29952.0, "max": 989928.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989928.0, "min": 29952.0, "max": 989928.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.4348512589931488, "min": -0.10489941388368607, "max": 0.4354470372200012, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 116.10528564453125, "min": -25.175859451293945, "max": 119.31248474121094, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.004547546152025461, "min": 0.004547546152025461, "max": 0.36418765783309937, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 1.2141947746276855, "min": 1.2141947746276855, "max": 87.76922607421875, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0695546594631326, "min": 0.06612098068227151, "max": 0.07402729547130275, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9737652324838565, "min": 0.48536103951374077, "max": 1.0363821365982386, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.012371094881105124, "min": 0.00014922986569510245, "max": 0.01452351471587982, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.17319532833547174, "min": 0.0019399882540363318, "max": 0.2033292060223175, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.602011751742854e-06, "min": 7.602011751742854e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010642816452439995, "min": 0.00010642816452439995, "max": 0.0033743275752241993, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10253397142857144, "min": 0.10253397142857144, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4354756000000002, "min": 1.3886848, "max": 2.4247758000000004, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002631437457142856, "min": 0.0002631437457142856, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036840124399999986, "min": 0.0036840124399999986, "max": 0.11249510241999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.013750982470810413, "min": 0.013750982470810413, "max": 0.45424920320510864, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.19251374900341034, "min": 0.19251374900341034, "max": 3.1797444820404053, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 443.8358208955224, "min": 424.79411764705884, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29737.0, "min": 15984.0, "max": 33007.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.3172925149104489, "min": -1.0000000521540642, "max": 1.5153371281921864, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 88.25859849900007, "min": -31.994001656770706, "max": 106.07359897345304, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.3172925149104489, "min": -1.0000000521540642, "max": 1.5153371281921864, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 88.25859849900007, "min": -31.994001656770706, "max": 106.07359897345304, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.06301433138624042, "min": 0.06301433138624042, "max": 8.733287941664457, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.221960202878108, "min": 4.221960202878108, "max": 139.73260706663132, "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": "1792115792", "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": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1792117787" }, "total": 1995.7996355390005, "count": 1, "self": 0.4324519000001601, "children": { "run_training.setup": { "total": 0.02422655499958637, "count": 1, "self": 0.02422655499958637 }, "TrainerController.start_learning": { "total": 1995.3429570840008, "count": 1, "self": 1.2309755459846201, "children": { "TrainerController._reset_env": { "total": 2.1661516819995086, "count": 1, "self": 2.1661516819995086 }, "TrainerController.advance": { "total": 1991.875088401017, "count": 63629, "self": 1.299382516890546, "children": { "env_step": { "total": 1406.0940147240944, "count": 63629, "self": 1264.8886133401102, "children": { "SubprocessEnvManager._take_step": { "total": 140.44422233388013, "count": 63629, "self": 4.3816297439107075, "children": { "TorchPolicy.evaluate": { "total": 136.06259258996943, "count": 62566, "self": 136.06259258996943 } } }, "workers": { "total": 0.7611790501041469, "count": 63629, "self": 0.0, "children": { "worker_root": { "total": 1992.0975164960946, "count": 63629, "is_parallel": true, "self": 830.3320344191707, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001897669999380014, "count": 1, "is_parallel": true, "self": 0.0006412020011339337, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012564679982460802, "count": 8, "is_parallel": true, "self": 0.0012564679982460802 } } }, "UnityEnvironment.step": { "total": 0.05260491899935005, "count": 1, "is_parallel": true, "self": 0.0005653959988194401, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005371490005927626, "count": 1, "is_parallel": true, "self": 0.0005371490005927626 }, "communicator.exchange": { "total": 0.04983469800026796, "count": 1, "is_parallel": true, "self": 0.04983469800026796 }, "steps_from_proto": { "total": 0.001667675999669882, "count": 1, "is_parallel": true, "self": 0.0003531499987730058, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013145260008968762, "count": 8, "is_parallel": true, "self": 0.0013145260008968762 } } } } } } }, "UnityEnvironment.step": { "total": 1161.765482076924, "count": 63628, "is_parallel": true, "self": 32.47940144399945, "children": { "UnityEnvironment._generate_step_input": { "total": 22.60668018494107, "count": 63628, "is_parallel": true, "self": 22.60668018494107 }, "communicator.exchange": { "total": 1008.5040401961451, "count": 63628, "is_parallel": true, "self": 1008.5040401961451 }, "steps_from_proto": { "total": 98.17536025183836, "count": 63628, "is_parallel": true, "self": 19.74029933298334, "children": { "_process_rank_one_or_two_observation": { "total": 78.43506091885502, "count": 509024, "is_parallel": true, "self": 78.43506091885502 } } } } } } } } } } }, "trainer_advance": { "total": 584.4816911600319, "count": 63629, "self": 2.471799300085877, "children": { "process_trajectory": { "total": 102.28234802795305, "count": 63629, "self": 102.09099287395293, "children": { "RLTrainer._checkpoint": { "total": 0.19135515400012082, "count": 2, "self": 0.19135515400012082 } } }, "_update_policy": { "total": 479.727543831993, "count": 448, "self": 255.8629906730057, "children": { "TorchPPOOptimizer.update": { "total": 223.8645531589873, "count": 22773, "self": 223.8645531589873 } } } } } } }, "trainer_threads": { "total": 8.819997674436308e-07, "count": 1, "self": 8.819997674436308e-07 }, "TrainerController._save_models": { "total": 0.07074057299996639, "count": 1, "self": 0.000892019000275468, "children": { "RLTrainer._checkpoint": { "total": 0.06984855399969092, "count": 1, "self": 0.06984855399969092 } } } } } } }