{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3457661271095276, "min": 0.33094489574432373, "max": 1.525981068611145, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 10306.5966796875, "min": 9896.576171875, "max": 46292.16015625, "count": 33 }, "Pyramids.Step.mean": { "value": 989894.0, "min": 29952.0, "max": 989894.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989894.0, "min": 29952.0, "max": 989894.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6317934989929199, "min": -0.15873882174491882, "max": 0.7322924733161926, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 178.165771484375, "min": -37.62110137939453, "max": 214.5616912841797, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.011644010432064533, "min": -0.011215832084417343, "max": 0.276326060295105, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.2836108207702637, "min": -3.1740806102752686, "max": 65.48927307128906, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06728802300904518, "min": 0.064293004933279, "max": 0.07219846899686733, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9420323221266326, "min": 0.4770850770897365, "max": 1.0612714933630938, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016991046050940744, "min": 0.0004287359676800233, "max": 0.016991046050940744, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.23787464471317044, "min": 0.005573567579840303, "max": 0.24364754744359135, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.567918905964289e-06, "min": 7.567918905964289e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010595086468350004, "min": 0.00010595086468350004, "max": 0.0037591792469402995, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10252260714285714, "min": 0.10252260714285714, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4353165, "min": 1.3886848, "max": 2.6530597, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002620084535714287, "min": 0.0002620084535714287, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036681183500000022, "min": 0.0036681183500000022, "max": 0.12532066403, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.012812330387532711, "min": 0.012756831012666225, "max": 0.3767855763435364, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1793726235628128, "min": 0.1793726235628128, "max": 2.6374990940093994, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 298.3796296296296, "min": 252.02564102564102, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 32225.0, "min": 15984.0, "max": 33185.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6275296121559761, "min": -1.0000000521540642, "max": 1.7470683651602166, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 175.77319811284542, "min": -29.523401588201523, "max": 204.40699872374535, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6275296121559761, "min": -1.0000000521540642, "max": 1.7470683651602166, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 175.77319811284542, "min": -29.523401588201523, "max": 204.40699872374535, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03970983305151566, "min": 0.035226678964781426, "max": 7.638066818471998, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.288661969563691, "min": 3.9313579552836018, "max": 122.20906909555197, "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": "1773703316", "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": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1773704059" }, "total": 743.4418234529999, "count": 1, "self": 0.21713197999997647, "children": { "run_training.setup": { "total": 0.009822649999932764, "count": 1, "self": 0.009822649999932764 }, "TrainerController.start_learning": { "total": 743.214868823, "count": 1, "self": 0.5112542870233483, "children": { "TrainerController._reset_env": { "total": 1.0357648019999033, "count": 1, "self": 1.0357648019999033 }, "TrainerController.advance": { "total": 741.6405163839768, "count": 64239, "self": 0.5008220429522225, "children": { "env_step": { "total": 497.35672474505145, "count": 64239, "self": 441.5007463210254, "children": { "SubprocessEnvManager._take_step": { "total": 55.51292721204345, "count": 64239, "self": 1.8631529241251883, "children": { "TorchPolicy.evaluate": { "total": 53.64977428791826, "count": 62544, "self": 53.64977428791826 } } }, "workers": { "total": 0.3430512119825835, "count": 64239, "self": 0.0, "children": { "worker_root": { "total": 742.2797814049868, "count": 64239, "is_parallel": true, "self": 335.9772895169476, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.000719170000138547, "count": 1, "is_parallel": true, "self": 0.00020991000019421335, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005092599999443337, "count": 8, "is_parallel": true, "self": 0.0005092599999443337 } } }, "UnityEnvironment.step": { "total": 0.016462120000142022, "count": 1, "is_parallel": true, "self": 0.00016693000043233042, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00017733999993652105, "count": 1, "is_parallel": true, "self": 0.00017733999993652105 }, "communicator.exchange": { "total": 0.015667349999603175, "count": 1, "is_parallel": true, "self": 0.015667349999603175 }, "steps_from_proto": { "total": 0.0004505000001699955, "count": 1, "is_parallel": true, "self": 0.00011605000054260017, "children": { "_process_rank_one_or_two_observation": { "total": 0.0003344499996273953, "count": 8, "is_parallel": true, "self": 0.0003344499996273953 } } } } } } }, "UnityEnvironment.step": { "total": 406.3024918880392, "count": 64238, "is_parallel": true, "self": 7.458636965071037, "children": { "UnityEnvironment._generate_step_input": { "total": 4.923684438002965, "count": 64238, "is_parallel": true, "self": 4.923684438002965 }, "communicator.exchange": { "total": 373.7024504629785, "count": 64238, "is_parallel": true, "self": 373.7024504629785 }, "steps_from_proto": { "total": 20.21772002198668, "count": 64238, "is_parallel": true, "self": 4.047622756349483, "children": { "_process_rank_one_or_two_observation": { "total": 16.170097265637196, "count": 513904, "is_parallel": true, "self": 16.170097265637196 } } } } } } } } } } }, "trainer_advance": { "total": 243.7829695959731, "count": 64239, "self": 0.8620753629766114, "children": { "process_trajectory": { "total": 49.10050290899471, "count": 64239, "self": 49.0303554889947, "children": { "RLTrainer._checkpoint": { "total": 0.07014742000001206, "count": 2, "self": 0.07014742000001206 } } }, "_update_policy": { "total": 193.82039132400178, "count": 456, "self": 111.92872913099245, "children": { "TorchPPOOptimizer.update": { "total": 81.89166219300932, "count": 22809, "self": 81.89166219300932 } } } } } } }, "trainer_threads": { "total": 6.800000846851617e-07, "count": 1, "self": 6.800000846851617e-07 }, "TrainerController._save_models": { "total": 0.027332669999850623, "count": 1, "self": 0.00046753999959037174, "children": { "RLTrainer._checkpoint": { "total": 0.02686513000026025, "count": 1, "self": 0.02686513000026025 } } } } } } }