{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5595940351486206, "min": 0.5595940351486206, "max": 1.428186297416687, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 16734.099609375, "min": 16734.099609375, "max": 43325.4609375, "count": 33 }, "Pyramids.Step.mean": { "value": 989882.0, "min": 29952.0, "max": 989882.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989882.0, "min": 29952.0, "max": 989882.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.2706109881401062, "min": -0.10828839987516403, "max": 0.3357340693473816, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 70.35885620117188, "min": -26.097503662109375, "max": 86.95512390136719, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.020055972039699554, "min": 0.005806599278002977, "max": 0.3922070264816284, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 5.214552879333496, "min": 1.4342299699783325, "max": 92.95306396484375, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06774020778781657, "min": 0.06494338701200572, "max": 0.07545740043021275, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.948362909029432, "min": 0.48899521709930954, "max": 1.092531178716408, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.012727970670745156, "min": 0.00030545791853573345, "max": 0.012727970670745156, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.17819158939043217, "min": 0.0024436633482858676, "max": 0.17819158939043217, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.44573323240714e-06, "min": 7.44573323240714e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010424026525369996, "min": 0.00010424026525369996, "max": 0.0032606762131080005, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10248187857142857, "min": 0.10248187857142857, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4347463, "min": 1.3691136000000002, "max": 2.4015442, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025793966928571436, "min": 0.00025793966928571436, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036111553700000007, "min": 0.0036111553700000007, "max": 0.10871051080000002, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.011782148852944374, "min": 0.01161551009863615, "max": 0.444497674703598, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.16495008766651154, "min": 0.16261714696884155, "max": 3.1114838123321533, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 505.49152542372883, "min": 505.49152542372883, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29824.0, "min": 15984.0, "max": 33229.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.2571491165939024, "min": -1.0000000521540642, "max": 1.2571491165939024, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 74.17179787904024, "min": -32.000001668930054, "max": 74.17179787904024, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.2571491165939024, "min": -1.0000000521540642, "max": 1.2571491165939024, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 74.17179787904024, "min": -32.000001668930054, "max": 74.17179787904024, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.06266893894545797, "min": 0.06266893894545797, "max": 9.560032261535525, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.6974673977820203, "min": 3.581360113923438, "max": 152.9605161845684, "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": "1742738188", "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": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1742741533" }, "total": 3344.926562358, "count": 1, "self": 1.1682831799998894, "children": { "run_training.setup": { "total": 0.054431976000046234, "count": 1, "self": 0.054431976000046234 }, "TrainerController.start_learning": { "total": 3343.703847202, "count": 1, "self": 2.406261236001228, "children": { "TrainerController._reset_env": { "total": 4.881691968999917, "count": 1, "self": 4.881691968999917 }, "TrainerController.advance": { "total": 3336.262599509999, "count": 63433, "self": 2.76560746404175, "children": { "env_step": { "total": 2174.6303590569887, "count": 63433, "self": 1998.9682861579872, "children": { "SubprocessEnvManager._take_step": { "total": 174.20511652898256, "count": 63433, "self": 7.759054275016524, "children": { "TorchPolicy.evaluate": { "total": 166.44606225396603, "count": 62565, "self": 166.44606225396603 } } }, "workers": { "total": 1.4569563700189292, "count": 63433, "self": 0.0, "children": { "worker_root": { "total": 3335.6567259110857, "count": 63433, "is_parallel": true, "self": 1522.9690871091182, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.007875701999978446, "count": 1, "is_parallel": true, "self": 0.005112623000059102, "children": { "_process_rank_one_or_two_observation": { "total": 0.002763078999919344, "count": 8, "is_parallel": true, "self": 0.002763078999919344 } } }, "UnityEnvironment.step": { "total": 0.07210384600000452, "count": 1, "is_parallel": true, "self": 0.0007109340000397424, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005340879999948811, "count": 1, "is_parallel": true, "self": 0.0005340879999948811 }, "communicator.exchange": { "total": 0.0686157989999856, "count": 1, "is_parallel": true, "self": 0.0686157989999856 }, "steps_from_proto": { "total": 0.0022430249999843, "count": 1, "is_parallel": true, "self": 0.0006607240002267645, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015823009997575355, "count": 8, "is_parallel": true, "self": 0.0015823009997575355 } } } } } } }, "UnityEnvironment.step": { "total": 1812.6876388019675, "count": 63432, "is_parallel": true, "self": 49.590588820990206, "children": { "UnityEnvironment._generate_step_input": { "total": 31.741837957965345, "count": 63432, "is_parallel": true, "self": 31.741837957965345 }, "communicator.exchange": { "total": 1599.27768190295, "count": 63432, "is_parallel": true, "self": 1599.27768190295 }, "steps_from_proto": { "total": 132.07753012006208, "count": 63432, "is_parallel": true, "self": 28.799194572936244, "children": { "_process_rank_one_or_two_observation": { "total": 103.27833554712583, "count": 507456, "is_parallel": true, "self": 103.27833554712583 } } } } } } } } } } }, "trainer_advance": { "total": 1158.8666329889681, "count": 63433, "self": 4.5578885919992445, "children": { "process_trajectory": { "total": 175.25641064896547, "count": 63433, "self": 174.69856419996597, "children": { "RLTrainer._checkpoint": { "total": 0.5578464489994985, "count": 2, "self": 0.5578464489994985 } } }, "_update_policy": { "total": 979.0523337480033, "count": 439, "self": 377.92158704300175, "children": { "TorchPPOOptimizer.update": { "total": 601.1307467050016, "count": 22785, "self": 601.1307467050016 } } } } } } }, "trainer_threads": { "total": 1.5600003280269448e-06, "count": 1, "self": 1.5600003280269448e-06 }, "TrainerController._save_models": { "total": 0.1532929269997112, "count": 1, "self": 0.003061779999825376, "children": { "RLTrainer._checkpoint": { "total": 0.15023114699988582, "count": 1, "self": 0.15023114699988582 } } } } } } }