{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.6271998286247253, "min": 0.6165434122085571, "max": 1.4295916557312012, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 18815.994140625, "min": 18456.84375, "max": 43368.09375, "count": 33 }, "Pyramids.Step.mean": { "value": 989945.0, "min": 29952.0, "max": 989945.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989945.0, "min": 29952.0, "max": 989945.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.2134125977754593, "min": -0.10973197221755981, "max": 0.24570702016353607, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 56.12751388549805, "min": -26.116209030151367, "max": 62.900997161865234, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.051950905472040176, "min": -0.051950905472040176, "max": 0.2349691390991211, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -13.663087844848633, "min": -13.663087844848633, "max": 55.687686920166016, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06982377532363154, "min": 0.06494333167176175, "max": 0.07213333810193881, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9775328545308416, "min": 0.4877267189065648, "max": 1.0786329878513545, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014873642754863381, "min": 4.914647537650513e-05, "max": 0.014873642754863381, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.20823099856808733, "min": 0.0005897577045180615, "max": 0.20823099856808733, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.28521185734286e-06, "min": 7.28521185734286e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010199296600280003, "min": 0.00010199296600280003, "max": 0.0031182637605788, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10242837142857143, "min": 0.10242837142857143, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4339972, "min": 1.3691136000000002, "max": 2.2394212000000002, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025259430571428573, "min": 0.00025259430571428573, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035363202800000005, "min": 0.0035363202800000005, "max": 0.10395817788, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.014616546221077442, "min": 0.014037981629371643, "max": 0.3774718642234802, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.20463164150714874, "min": 0.196531742811203, "max": 2.642302989959717, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 555.0847457627119, "min": 555.0847457627119, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 32750.0, "min": 15984.0, "max": 33039.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.0719559013338413, "min": -1.0000000521540642, "max": 1.0719559013338413, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 63.24539817869663, "min": -32.000001668930054, "max": 63.24539817869663, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.0719559013338413, "min": -1.0000000521540642, "max": 1.0719559013338413, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 63.24539817869663, "min": -32.000001668930054, "max": 63.24539817869663, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.08365024718696694, "min": 0.08365024718696694, "max": 7.882524403743446, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.935364584031049, "min": 4.226075328304432, "max": 126.12039045989513, "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": "1722703271", "python_version": "3.10.12 (main, Jul 29 2024, 16:56:48) [GCC 11.4.0]", "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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1722705350" }, "total": 2079.5245931279997, "count": 1, "self": 0.6484097050001765, "children": { "run_training.setup": { "total": 0.05446190799966644, "count": 1, "self": 0.05446190799966644 }, "TrainerController.start_learning": { "total": 2078.821721515, "count": 1, "self": 1.6629063040486471, "children": { "TrainerController._reset_env": { "total": 1.861216395000156, "count": 1, "self": 1.861216395000156 }, "TrainerController.advance": { "total": 2075.1626938289514, "count": 63127, "self": 1.4423170149761972, "children": { "env_step": { "total": 1435.2765055929685, "count": 63127, "self": 1298.6962982339287, "children": { "SubprocessEnvManager._take_step": { "total": 135.74926724999887, "count": 63127, "self": 4.792438003952157, "children": { "TorchPolicy.evaluate": { "total": 130.9568292460467, "count": 62570, "self": 130.9568292460467 } } }, "workers": { "total": 0.8309401090409665, "count": 63127, "self": 0.0, "children": { "worker_root": { "total": 2073.6515817810296, "count": 63127, "is_parallel": true, "self": 896.3342319549893, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0024978649998956826, "count": 1, "is_parallel": true, "self": 0.0008220550002988603, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016758099995968223, "count": 8, "is_parallel": true, "self": 0.0016758099995968223 } } }, "UnityEnvironment.step": { "total": 0.05154255000024932, "count": 1, "is_parallel": true, "self": 0.0006683209999209794, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004681909999817435, "count": 1, "is_parallel": true, "self": 0.0004681909999817435 }, "communicator.exchange": { "total": 0.04867992800018328, "count": 1, "is_parallel": true, "self": 0.04867992800018328 }, "steps_from_proto": { "total": 0.0017261100001633167, "count": 1, "is_parallel": true, "self": 0.0003852059999189805, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013409040002443362, "count": 8, "is_parallel": true, "self": 0.0013409040002443362 } } } } } } }, "UnityEnvironment.step": { "total": 1177.3173498260403, "count": 63126, "is_parallel": true, "self": 33.40795773587797, "children": { "UnityEnvironment._generate_step_input": { "total": 24.269760381966535, "count": 63126, "is_parallel": true, "self": 24.269760381966535 }, "communicator.exchange": { "total": 1019.6345521951112, "count": 63126, "is_parallel": true, "self": 1019.6345521951112 }, "steps_from_proto": { "total": 100.00507951308464, "count": 63126, "is_parallel": true, "self": 20.548530650930843, "children": { "_process_rank_one_or_two_observation": { "total": 79.4565488621538, "count": 505008, "is_parallel": true, "self": 79.4565488621538 } } } } } } } } } } }, "trainer_advance": { "total": 638.4438712210067, "count": 63127, "self": 2.272441346016876, "children": { "process_trajectory": { "total": 130.26845735699135, "count": 63127, "self": 130.02693367099164, "children": { "RLTrainer._checkpoint": { "total": 0.24152368599970941, "count": 2, "self": 0.24152368599970941 } } }, "_update_policy": { "total": 505.9029725179985, "count": 417, "self": 300.112696347016, "children": { "TorchPPOOptimizer.update": { "total": 205.79027617098245, "count": 22866, "self": 205.79027617098245 } } } } } } }, "trainer_threads": { "total": 1.6149997463799082e-06, "count": 1, "self": 1.6149997463799082e-06 }, "TrainerController._save_models": { "total": 0.13490337199982605, "count": 1, "self": 0.0019458309998299228, "children": { "RLTrainer._checkpoint": { "total": 0.13295754099999613, "count": 1, "self": 0.13295754099999613 } } } } } } }