{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3985128402709961, "min": 0.3985128402709961, "max": 1.4250582456588745, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 11968.1376953125, "min": 11968.1376953125, "max": 43230.56640625, "count": 33 }, "Pyramids.Step.mean": { "value": 989926.0, "min": 29952.0, "max": 989926.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989926.0, "min": 29952.0, "max": 989926.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.49703291058540344, "min": -0.09607508778572083, "max": 0.5508319735527039, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 134.19888305664062, "min": -23.154096603393555, "max": 151.47879028320312, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.7648010849952698, "min": -0.04160233959555626, "max": 0.7648010849952698, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 206.4962921142578, "min": -11.23263168334961, "max": 206.4962921142578, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0671511386248139, "min": 0.06203181934748393, "max": 0.07349810226697227, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9401159407473945, "min": 0.476691065133675, "max": 1.0417973818063424, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.07791749431496663, "min": 0.0009491389103805703, "max": 0.07791749431496663, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 1.0908449204095327, "min": 0.013287944745327985, "max": 1.0908449204095327, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.447083231957141e-06, "min": 7.447083231957141e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010425916524739998, "min": 0.00010425916524739998, "max": 0.0036326377891207993, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1024823285714286, "min": 0.1024823285714286, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4347526000000004, "min": 1.3886848, "max": 2.6108792, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002579846242857143, "min": 0.0002579846242857143, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036117847400000008, "min": 0.0036117847400000008, "max": 0.12110683208000002, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010948874056339264, "min": 0.010948874056339264, "max": 0.34054917097091675, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1532842367887497, "min": 0.1532842367887497, "max": 2.3838441371917725, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 392.12987012987014, "min": 337.9230769230769, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30194.0, "min": 15984.0, "max": 33747.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.4259895970682046, "min": -1.0000000521540642, "max": 1.5961230604366943, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 109.80119897425175, "min": -27.77800177037716, "max": 145.24719849973917, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.4259895970682046, "min": -1.0000000521540642, "max": 1.5961230604366943, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 109.80119897425175, "min": -27.77800177037716, "max": 145.24719849973917, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04458817188773915, "min": 0.039609910372406715, "max": 6.980756579898298, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.4332892353559146, "min": 3.4332892353559146, "max": 111.69210527837276, "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": "1730589639", "python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.5.0+cpu", "numpy_version": "1.23.5", "end_time_seconds": "1730591426" }, "total": 1787.0415409900006, "count": 1, "self": 0.373002978999466, "children": { "run_training.setup": { "total": 0.038286298000457464, "count": 1, "self": 0.038286298000457464 }, "TrainerController.start_learning": { "total": 1786.6302517130007, "count": 1, "self": 1.127370783972765, "children": { "TrainerController._reset_env": { "total": 2.0866846729995814, "count": 1, "self": 2.0866846729995814 }, "TrainerController.advance": { "total": 1783.3579601370284, "count": 63761, "self": 1.158777245260353, "children": { "env_step": { "total": 1194.228612107796, "count": 63761, "self": 1099.5291666494913, "children": { "SubprocessEnvManager._take_step": { "total": 94.00252255510895, "count": 63761, "self": 4.61589642704439, "children": { "TorchPolicy.evaluate": { "total": 89.38662612806456, "count": 62548, "self": 89.38662612806456 } } }, "workers": { "total": 0.6969229031956274, "count": 63761, "self": 0.0, "children": { "worker_root": { "total": 1784.6328203110397, "count": 63761, "is_parallel": true, "self": 778.2691212737764, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0020966619995306246, "count": 1, "is_parallel": true, "self": 0.0006274339975789189, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014692280019517057, "count": 8, "is_parallel": true, "self": 0.0014692280019517057 } } }, "UnityEnvironment.step": { "total": 0.03583086800063029, "count": 1, "is_parallel": true, "self": 0.00039991800076677464, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003194680002707173, "count": 1, "is_parallel": true, "self": 0.0003194680002707173 }, "communicator.exchange": { "total": 0.033998378999967827, "count": 1, "is_parallel": true, "self": 0.033998378999967827 }, "steps_from_proto": { "total": 0.0011131029996249708, "count": 1, "is_parallel": true, "self": 0.00024280000070575625, "children": { "_process_rank_one_or_two_observation": { "total": 0.0008703029989192146, "count": 8, "is_parallel": true, "self": 0.0008703029989192146 } } } } } } }, "UnityEnvironment.step": { "total": 1006.3636990372634, "count": 63760, "is_parallel": true, "self": 20.10865924925656, "children": { "UnityEnvironment._generate_step_input": { "total": 12.80891040489405, "count": 63760, "is_parallel": true, "self": 12.80891040489405 }, "communicator.exchange": { "total": 915.7622297730686, "count": 63760, "is_parallel": true, "self": 915.7622297730686 }, "steps_from_proto": { "total": 57.683899610044136, "count": 63760, "is_parallel": true, "self": 12.312333334079995, "children": { "_process_rank_one_or_two_observation": { "total": 45.37156627596414, "count": 510080, "is_parallel": true, "self": 45.37156627596414 } } } } } } } } } } }, "trainer_advance": { "total": 587.9705707839721, "count": 63761, "self": 2.3847700588039515, "children": { "process_trajectory": { "total": 116.29864065515449, "count": 63761, "self": 115.94877572515452, "children": { "RLTrainer._checkpoint": { "total": 0.349864929999967, "count": 2, "self": 0.349864929999967 } } }, "_update_policy": { "total": 469.28716007001367, "count": 456, "self": 253.05291288792705, "children": { "TorchPPOOptimizer.update": { "total": 216.23424718208662, "count": 22791, "self": 216.23424718208662 } } } } } } }, "trainer_threads": { "total": 1.116999555961229e-06, "count": 1, "self": 1.116999555961229e-06 }, "TrainerController._save_models": { "total": 0.05823500200040144, "count": 1, "self": 0.0014622730004703044, "children": { "RLTrainer._checkpoint": { "total": 0.05677272899993113, "count": 1, "self": 0.05677272899993113 } } } } } } }