{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4484938085079193, "min": 0.4484938085079193, "max": 1.507041573524475, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 13361.52734375, "min": 13361.52734375, "max": 45717.61328125, "count": 33 }, "Pyramids.Step.mean": { "value": 989890.0, "min": 29952.0, "max": 989890.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989890.0, "min": 29952.0, "max": 989890.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.24449053406715393, "min": -0.08303222805261612, "max": 0.34761524200439453, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 62.34508514404297, "min": -19.927734375, "max": 90.37995910644531, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -1.879557490348816, "min": -1.9528666734695435, "max": 2.180330753326416, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -479.28717041015625, "min": -509.6982116699219, "max": 566.885986328125, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0711138052494524, "min": 0.06491783739918554, "max": 0.07402172435731044, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9955932734923337, "min": 0.48381534922532143, "max": 1.0571641896830817, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.523038732927196, "min": 0.00012919346758292347, "max": 0.523038732927196, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 7.322542260980745, "min": 0.0018087085461609286, "max": 7.322542260980745, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.289090427478574e-06, "min": 7.289090427478574e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010204726598470004, "min": 0.00010204726598470004, "max": 0.0032558954147015994, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10242966428571428, "min": 0.10242966428571428, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4340152999999998, "min": 1.3691136000000002, "max": 2.4431072000000005, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002527234621428573, "min": 0.0002527234621428573, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003538128470000002, "min": 0.003538128470000002, "max": 0.10855131016000003, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009125393815338612, "min": 0.009125393815338612, "max": 0.41734614968299866, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.12775550782680511, "min": 0.12775550782680511, "max": 2.9214229583740234, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 571.2307692307693, "min": 495.52542372881356, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29704.0, "min": 15984.0, "max": 32747.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.0825345877271433, "min": -1.0000000521540642, "max": 1.2685573508993524, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 56.29179856181145, "min": -32.000001668930054, "max": 77.3819984048605, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.0825345877271433, "min": -1.0000000521540642, "max": 1.2685573508993524, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 56.29179856181145, "min": -32.000001668930054, "max": 77.3819984048605, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.054566108950754054, "min": 0.05042585650493284, "max": 8.928653911687434, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.837437665439211, "min": 2.837437665439211, "max": 142.85846258699894, "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": "1750681963", "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": "2.7.1+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1750684028" }, "total": 2064.788200636, "count": 1, "self": 0.5462420210001255, "children": { "run_training.setup": { "total": 0.023352799999997842, "count": 1, "self": 0.023352799999997842 }, "TrainerController.start_learning": { "total": 2064.218605815, "count": 1, "self": 1.2372683429771314, "children": { "TrainerController._reset_env": { "total": 3.893654857999991, "count": 1, "self": 3.893654857999991 }, "TrainerController.advance": { "total": 2059.007950086023, "count": 63415, "self": 1.3015567399934298, "children": { "env_step": { "total": 1410.5149525910017, "count": 63415, "self": 1266.0507895819883, "children": { "SubprocessEnvManager._take_step": { "total": 143.72092754401172, "count": 63415, "self": 4.353773891001765, "children": { "TorchPolicy.evaluate": { "total": 139.36715365300995, "count": 62571, "self": 139.36715365300995 } } }, "workers": { "total": 0.7432354650015895, "count": 63415, "self": 0.0, "children": { "worker_root": { "total": 2059.430335816015, "count": 63415, "is_parallel": true, "self": 900.7864853950146, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006355205999966529, "count": 1, "is_parallel": true, "self": 0.00448609399995803, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018691120000084993, "count": 8, "is_parallel": true, "self": 0.0018691120000084993 } } }, "UnityEnvironment.step": { "total": 0.046859011000037754, "count": 1, "is_parallel": true, "self": 0.0005552520000264849, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004497239999636804, "count": 1, "is_parallel": true, "self": 0.0004497239999636804 }, "communicator.exchange": { "total": 0.04431933000000754, "count": 1, "is_parallel": true, "self": 0.04431933000000754 }, "steps_from_proto": { "total": 0.0015347050000400486, "count": 1, "is_parallel": true, "self": 0.0003312390000473897, "children": { "_process_rank_one_or_two_observation": { "total": 0.001203465999992659, "count": 8, "is_parallel": true, "self": 0.001203465999992659 } } } } } } }, "UnityEnvironment.step": { "total": 1158.6438504210005, "count": 63414, "is_parallel": true, "self": 31.204137168012494, "children": { "UnityEnvironment._generate_step_input": { "total": 21.797103267958278, "count": 63414, "is_parallel": true, "self": 21.797103267958278 }, "communicator.exchange": { "total": 1014.5155729170086, "count": 63414, "is_parallel": true, "self": 1014.5155729170086 }, "steps_from_proto": { "total": 91.12703706802108, "count": 63414, "is_parallel": true, "self": 17.963086770020368, "children": { "_process_rank_one_or_two_observation": { "total": 73.16395029800071, "count": 507312, "is_parallel": true, "self": 73.16395029800071 } } } } } } } } } } }, "trainer_advance": { "total": 647.1914407550277, "count": 63415, "self": 2.358597632058718, "children": { "process_trajectory": { "total": 121.70408041196868, "count": 63415, "self": 121.42279381996866, "children": { "RLTrainer._checkpoint": { "total": 0.28128659200001493, "count": 2, "self": 0.28128659200001493 } } }, "_update_policy": { "total": 523.1287627110003, "count": 443, "self": 290.450171928984, "children": { "TorchPPOOptimizer.update": { "total": 232.67859078201627, "count": 22788, "self": 232.67859078201627 } } } } } } }, "trainer_threads": { "total": 1.0579997251625173e-06, "count": 1, "self": 1.0579997251625173e-06 }, "TrainerController._save_models": { "total": 0.07973147000029712, "count": 1, "self": 0.0012926150006933312, "children": { "RLTrainer._checkpoint": { "total": 0.07843885499960379, "count": 1, "self": 0.07843885499960379 } } } } } } }