{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.1518215537071228, "min": 0.12530633807182312, "max": 1.4746869802474976, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 4561.93408203125, "min": 3747.16064453125, "max": 44736.10546875, "count": 100 }, "Pyramids.Step.mean": { "value": 2999885.0, "min": 29952.0, "max": 2999885.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999885.0, "min": 29952.0, "max": 2999885.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.7477790713310242, "min": -0.16893930733203888, "max": 0.7882753610610962, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 217.6037139892578, "min": -40.03861618041992, "max": 234.9060516357422, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.006888110190629959, "min": -0.034016888588666916, "max": 0.46843382716178894, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 2.0044400691986084, "min": -10.058513641357422, "max": 111.01881408691406, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06744729133911688, "min": 0.06402229578400563, "max": 0.07611466185127418, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9442620787476362, "min": 0.4871366739468101, "max": 1.0936850438883992, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015692226984630533, "min": 0.0005075364543951074, "max": 0.017195445221386167, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21969117778482747, "min": 0.004567828089555967, "max": 0.2579316783207925, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.524356634771428e-06, "min": 1.524356634771428e-06, "max": 0.00029838354339596195, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.134099288679999e-05, "min": 2.134099288679999e-05, "max": 0.003969285176904966, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10050808571428571, "min": 0.10050808571428571, "max": 0.19946118095238097, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4071132, "min": 1.3962282666666668, "max": 2.7230950333333337, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 6.075776285714284e-05, "min": 6.075776285714284e-05, "max": 0.009946171977142856, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.0008506086799999998, "min": 0.0008506086799999998, "max": 0.13231719382999999, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.006759076379239559, "min": 0.006660886108875275, "max": 0.4303519129753113, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.09462706744670868, "min": 0.09325240552425385, "max": 3.012463331222534, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 247.3362831858407, "min": 231.3709677419355, "max": 999.0, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 27949.0, "min": 15984.0, "max": 32930.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.699553973115651, "min": -1.0000000521540642, "max": 1.767563475502862, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 192.04959896206856, "min": -31.999601677060127, "max": 228.2193984389305, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.699553973115651, "min": -1.0000000521540642, "max": 1.767563475502862, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 192.04959896206856, "min": -31.999601677060127, "max": 228.2193984389305, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.017834546842892547, "min": 0.017414834326759335, "max": 8.30799985025078, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 2.015303793246858, "min": 2.015303793246858, "max": 132.9279976040125, "count": 100 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1700148984", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.0+cu118", "numpy_version": "1.23.5", "end_time_seconds": "1700157742" }, "total": 8757.640482693001, "count": 1, "self": 0.494850357003088, "children": { "run_training.setup": { "total": 0.052286706999893795, "count": 1, "self": 0.052286706999893795 }, "TrainerController.start_learning": { "total": 8757.093345628999, "count": 1, "self": 5.874912404779025, "children": { "TrainerController._reset_env": { "total": 1.3936546800000542, "count": 1, "self": 1.3936546800000542 }, "TrainerController.advance": { "total": 8749.74517216022, "count": 193940, "self": 6.251621759165573, "children": { "env_step": { "total": 5849.800360995107, "count": 193940, "self": 5452.370816935354, "children": { "SubprocessEnvManager._take_step": { "total": 393.91045222865273, "count": 193940, "self": 16.729529515847844, "children": { "TorchPolicy.evaluate": { "total": 377.1809227128049, "count": 187560, "self": 377.1809227128049 } } }, "workers": { "total": 3.519091831100468, "count": 193940, "self": 0.0, "children": { "worker_root": { "total": 8742.23770560066, "count": 193940, "is_parallel": true, "self": 3719.20009524945, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.003926331000002392, "count": 1, "is_parallel": true, "self": 0.0013773359999049717, "children": { "_process_rank_one_or_two_observation": { "total": 0.0025489950000974204, "count": 8, "is_parallel": true, "self": 0.0025489950000974204 } } }, "UnityEnvironment.step": { "total": 0.05148526700008915, "count": 1, "is_parallel": true, "self": 0.0005755269999099255, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00029091100009281945, "count": 1, "is_parallel": true, "self": 0.00029091100009281945 }, "communicator.exchange": { "total": 0.04893202600010227, "count": 1, "is_parallel": true, "self": 0.04893202600010227 }, "steps_from_proto": { "total": 0.0016868029999841383, "count": 1, "is_parallel": true, "self": 0.0003434739996919234, "children": { "_process_rank_one_or_two_observation": { "total": 0.001343329000292215, "count": 8, "is_parallel": true, "self": 0.001343329000292215 } } } } } } }, "UnityEnvironment.step": { "total": 5023.037610351211, "count": 193939, "is_parallel": true, "self": 114.31621535066915, "children": { "UnityEnvironment._generate_step_input": { "total": 64.94760058173188, "count": 193939, "is_parallel": true, "self": 64.94760058173188 }, "communicator.exchange": { "total": 4518.060588312846, "count": 193939, "is_parallel": true, "self": 4518.060588312846 }, "steps_from_proto": { "total": 325.71320610596285, "count": 193939, "is_parallel": true, "self": 70.00067494820951, "children": { "_process_rank_one_or_two_observation": { "total": 255.71253115775335, "count": 1551512, "is_parallel": true, "self": 255.71253115775335 } } } } } } } } } } }, "trainer_advance": { "total": 2893.693189405947, "count": 193940, "self": 11.047403916343683, "children": { "process_trajectory": { "total": 427.65439836461405, "count": 193940, "self": 427.1406205616124, "children": { "RLTrainer._checkpoint": { "total": 0.5137778030016307, "count": 6, "self": 0.5137778030016307 } } }, "_update_policy": { "total": 2454.991387124989, "count": 1390, "self": 1001.8047621549204, "children": { "TorchPPOOptimizer.update": { "total": 1453.1866249700688, "count": 68439, "self": 1453.1866249700688 } } } } } } }, "trainer_threads": { "total": 1.2700002116616815e-06, "count": 1, "self": 1.2700002116616815e-06 }, "TrainerController._save_models": { "total": 0.07960511400051473, "count": 1, "self": 0.001685033999820007, "children": { "RLTrainer._checkpoint": { "total": 0.07792008000069472, "count": 1, "self": 0.07792008000069472 } } } } } } }