{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.23216168582439423, "min": 0.22822752594947815, "max": 1.4686609506607056, "count": 68 }, "Pyramids.Policy.Entropy.sum": { "value": 6968.56494140625, "min": 6872.38720703125, "max": 44553.296875, "count": 68 }, "Pyramids.Step.mean": { "value": 2039939.0, "min": 29952.0, "max": 2039939.0, "count": 68 }, "Pyramids.Step.sum": { "value": 2039939.0, "min": 29952.0, "max": 2039939.0, "count": 68 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.8554800152778625, "min": -0.10093619674444199, "max": 0.8554800152778625, "count": 68 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 256.6440124511719, "min": -24.426559448242188, "max": 256.6440124511719, "count": 68 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.0081409877166152, "min": -0.03461739420890808, "max": 0.2912626266479492, "count": 68 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 2.442296266555786, "min": -9.935192108154297, "max": 70.19429016113281, "count": 68 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06831075437159077, "min": 0.06329921378831689, "max": 0.07736064368024621, "count": 68 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9563505612022708, "min": 0.49836566674304944, "max": 1.083049011523447, "count": 68 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.013814210268763073, "min": 0.0008615905706710742, "max": 0.01700291723967644, "count": 68 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.19339894376268302, "min": 0.011200677418723964, "max": 0.23804084135547018, "count": 68 }, "Pyramids.Policy.LearningRate.mean": { "value": 9.75223603497119e-05, "min": 9.75223603497119e-05, "max": 0.00029838354339596195, "count": 68 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0013653130448959664, "min": 0.0013653130448959664, "max": 0.00392742009086, "count": 68 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.13250743095238096, "min": 0.13250743095238096, "max": 0.19946118095238097, "count": 68 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.8551040333333333, "min": 1.3962282666666668, "max": 2.7091399999999997, "count": 68 }, "Pyramids.Policy.Beta.mean": { "value": 0.0032574923521428573, "min": 0.0032574923521428573, "max": 0.009946171977142856, "count": 68 }, "Pyramids.Policy.Beta.sum": { "value": 0.04560489293, "min": 0.04560489293, "max": 0.130923086, "count": 68 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.006816111970692873, "min": 0.006301645189523697, "max": 0.37930354475975037, "count": 68 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.0954255685210228, "min": 0.08822303265333176, "max": 2.6551249027252197, "count": 68 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 210.9794520547945, "min": 210.9794520547945, "max": 999.0, "count": 68 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30803.0, "min": 15984.0, "max": 33855.0, "count": 68 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7753150575883585, "min": -1.0000000521540642, "max": 1.7753150575883585, "count": 68 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 259.19599840790033, "min": -30.0198016166687, "max": 259.19599840790033, "count": 68 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7753150575883585, "min": -1.0000000521540642, "max": 1.7753150575883585, "count": 68 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 259.19599840790033, "min": -30.0198016166687, "max": 259.19599840790033, "count": 68 }, "Pyramids.Policy.RndReward.mean": { "value": 0.014890777429347309, "min": 0.014890777429347309, "max": 7.675238830037415, "count": 68 }, "Pyramids.Policy.RndReward.sum": { "value": 2.174053504684707, "min": 1.8585745868622325, "max": 122.80382128059864, "count": 68 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 68 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 68 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1780644297", "python_version": "3.10.11 (main, May 16 2023, 00:28:57) [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": "1780649675" }, "total": 5377.578943773, "count": 1, "self": 0.4792717000000266, "children": { "run_training.setup": { "total": 0.023006346000101985, "count": 1, "self": 0.023006346000101985 }, "TrainerController.start_learning": { "total": 5377.076665727, "count": 1, "self": 3.365448631909203, "children": { "TrainerController._reset_env": { "total": 2.148337442999946, "count": 1, "self": 2.148337442999946 }, "TrainerController.advance": { "total": 5371.561277016091, "count": 131610, "self": 3.4163277140623904, "children": { "env_step": { "total": 3978.422131251942, "count": 131610, "self": 3630.5817540216904, "children": { "SubprocessEnvManager._take_step": { "total": 345.8151303160721, "count": 131610, "self": 10.368254946965408, "children": { "TorchPolicy.evaluate": { "total": 335.4468753691067, "count": 127653, "self": 335.4468753691067 } } }, "workers": { "total": 2.0252469141794336, "count": 131609, "self": 0.0, "children": { "worker_root": { "total": 5364.83384016797, "count": 131609, "is_parallel": true, "self": 2002.134551953911, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017734300001848169, "count": 1, "is_parallel": true, "self": 0.0006051519999346056, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011682780002502113, "count": 8, "is_parallel": true, "self": 0.0011682780002502113 } } }, "UnityEnvironment.step": { "total": 0.05205409800009875, "count": 1, "is_parallel": true, "self": 0.0005910200002290367, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00045941899998069857, "count": 1, "is_parallel": true, "self": 0.00045941899998069857 }, "communicator.exchange": { "total": 0.04929057599997577, "count": 1, "is_parallel": true, "self": 0.04929057599997577 }, "steps_from_proto": { "total": 0.0017130829999132402, "count": 1, "is_parallel": true, "self": 0.00037201199938863283, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013410710005246074, "count": 8, "is_parallel": true, "self": 0.0013410710005246074 } } } } } } }, "UnityEnvironment.step": { "total": 3362.6992882140594, "count": 131608, "is_parallel": true, "self": 72.65770129504835, "children": { "UnityEnvironment._generate_step_input": { "total": 49.17720659810061, "count": 131608, "is_parallel": true, "self": 49.17720659810061 }, "communicator.exchange": { "total": 3006.3144070979442, "count": 131608, "is_parallel": true, "self": 3006.3144070979442 }, "steps_from_proto": { "total": 234.54997322296617, "count": 131608, "is_parallel": true, "self": 49.87128470466223, "children": { "_process_rank_one_or_two_observation": { "total": 184.67868851830394, "count": 1052864, "is_parallel": true, "self": 184.67868851830394 } } } } } } } } } } }, "trainer_advance": { "total": 1389.7228180500865, "count": 131609, "self": 6.597880311056542, "children": { "process_trajectory": { "total": 268.3150561860273, "count": 131609, "self": 267.9117552450273, "children": { "RLTrainer._checkpoint": { "total": 0.4033009409999977, "count": 4, "self": 0.4033009409999977 } } }, "_update_policy": { "total": 1114.8098815530027, "count": 939, "self": 611.7738963660115, "children": { "TorchPPOOptimizer.update": { "total": 503.0359851869912, "count": 46521, "self": 503.0359851869912 } } } } } } }, "trainer_threads": { "total": 1.3549997674999759e-06, "count": 1, "self": 1.3549997674999759e-06 }, "TrainerController._save_models": { "total": 0.0016012810001484468, "count": 1, "self": 2.6049000553030055e-05, "children": { "RLTrainer._checkpoint": { "total": 0.0015752319995954167, "count": 1, "self": 0.0015752319995954167 } } } } } } }