{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.30000659823417664, "min": 0.258798748254776, "max": 1.5920110940933228, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 3052.8671875, "min": 2443.06005859375, "max": 16302.193359375, "count": 100 }, "Pyramids.Step.mean": { "value": 999986.0, "min": 9984.0, "max": 999986.0, "count": 100 }, "Pyramids.Step.sum": { "value": 999986.0, "min": 9984.0, "max": 999986.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5499358177185059, "min": -0.1192140206694603, "max": 0.6204128861427307, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 52.24390411376953, "min": -9.298693656921387, "max": 60.08495330810547, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.04204211011528969, "min": -0.10756294429302216, "max": 0.21006692945957184, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -3.9940004348754883, "min": -8.389909744262695, "max": 17.01542091369629, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07075532483965315, "min": 0.06153705376709696, "max": 0.0802252916037105, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.3537766241982657, "min": 0.12898884922361012, "max": 0.37984483592056983, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.02000113251657846, "min": 0.00012082483644070296, "max": 0.021074817146576354, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.1000056625828923, "min": 0.00048329934576281185, "max": 0.10537408573288178, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.705239431619992e-06, "min": 1.705239431619992e-06, "max": 0.0002981568006144, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 8.52619715809996e-06, "min": 8.52619715809996e-06, "max": 0.0013125855624714997, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10056837999999999, "min": 0.10056837999999999, "max": 0.1993856, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 0.5028419, "min": 0.39319040000000005, "max": 0.9375285000000001, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 6.678116199999973e-05, "min": 6.678116199999973e-05, "max": 0.00993862144, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.0003339058099999986, "min": 0.0003339058099999986, "max": 0.043759097149999995, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.011616619303822517, "min": 0.010806536301970482, "max": 0.5640522241592407, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.05808309465646744, "min": 0.044529978185892105, "max": 1.1281044483184814, "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 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 328.51724137931035, "min": 257.7142857142857, "max": 999.0, "count": 97 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 9527.0, "min": 1518.0, "max": 16192.0, "count": 97 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6714827428603996, "min": -1.0000000521540642, "max": 1.7422857039741106, "count": 97 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 48.472999542951584, "min": -16.000000834465027, "max": 57.56099911034107, "count": 97 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6714827428603996, "min": -1.0000000521540642, "max": 1.7422857039741106, "count": 97 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 48.472999542951584, "min": -16.000000834465027, "max": 57.56099911034107, "count": 97 }, "Pyramids.Policy.RndReward.mean": { "value": 0.038445326564873664, "min": 0.02978555753569318, "max": 6.512202117592096, "count": 97 }, "Pyramids.Policy.RndReward.sum": { "value": 1.1149144703813363, "min": 0.8339956109994091, "max": 104.19523388147354, "count": 97 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1718993669", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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": "2.3.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1718996889" }, "total": 3220.544672016, "count": 1, "self": 0.6414611179998246, "children": { "run_training.setup": { "total": 0.07391135199998189, "count": 1, "self": 0.07391135199998189 }, "TrainerController.start_learning": { "total": 3219.829299546, "count": 1, "self": 2.2143268000222633, "children": { "TrainerController._reset_env": { "total": 3.590630725999972, "count": 1, "self": 3.590630725999972 }, "TrainerController.advance": { "total": 3213.940356200978, "count": 63947, "self": 2.3751910600053634, "children": { "env_step": { "total": 2155.859991976962, "count": 63947, "self": 2000.8544538319861, "children": { "SubprocessEnvManager._take_step": { "total": 153.61629361099955, "count": 63947, "self": 6.797375119011917, "children": { "TorchPolicy.evaluate": { "total": 146.81891849198763, "count": 62562, "self": 146.81891849198763 } } }, "workers": { "total": 1.3892445339764663, "count": 63947, "self": 0.0, "children": { "worker_root": { "total": 3212.8248841450013, "count": 63947, "is_parallel": true, "self": 1394.6657047959575, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006310171999984959, "count": 1, "is_parallel": true, "self": 0.004594010000005255, "children": { "_process_rank_one_or_two_observation": { "total": 0.001716161999979704, "count": 8, "is_parallel": true, "self": 0.001716161999979704 } } }, "UnityEnvironment.step": { "total": 0.062192127000002984, "count": 1, "is_parallel": true, "self": 0.0007758610000223598, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005398960000206898, "count": 1, "is_parallel": true, "self": 0.0005398960000206898 }, "communicator.exchange": { "total": 0.05891583299995773, "count": 1, "is_parallel": true, "self": 0.05891583299995773 }, "steps_from_proto": { "total": 0.001960537000002205, "count": 1, "is_parallel": true, "self": 0.0004162990000509126, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015442379999512923, "count": 8, "is_parallel": true, "self": 0.0015442379999512923 } } } } } } }, "UnityEnvironment.step": { "total": 1818.1591793490438, "count": 63946, "is_parallel": true, "self": 51.43103495506125, "children": { "UnityEnvironment._generate_step_input": { "total": 30.545134893028717, "count": 63946, "is_parallel": true, "self": 30.545134893028717 }, "communicator.exchange": { "total": 1605.4176317080094, "count": 63946, "is_parallel": true, "self": 1605.4176317080094 }, "steps_from_proto": { "total": 130.76537779294455, "count": 63946, "is_parallel": true, "self": 28.043975463002823, "children": { "_process_rank_one_or_two_observation": { "total": 102.72140232994172, "count": 511568, "is_parallel": true, "self": 102.72140232994172 } } } } } } } } } } }, "trainer_advance": { "total": 1055.7051731640104, "count": 63947, "self": 4.31213613801242, "children": { "process_trajectory": { "total": 163.62592018199888, "count": 63947, "self": 163.3514147519988, "children": { "RLTrainer._checkpoint": { "total": 0.2745054300000902, "count": 2, "self": 0.2745054300000902 } } }, "_update_policy": { "total": 887.7671168439991, "count": 452, "self": 370.02901919800127, "children": { "TorchPPOOptimizer.update": { "total": 517.7380976459979, "count": 22833, "self": 517.7380976459979 } } } } } } }, "trainer_threads": { "total": 1.1980000635958277e-06, "count": 1, "self": 1.1980000635958277e-06 }, "TrainerController._save_models": { "total": 0.08398462100012694, "count": 1, "self": 0.002250651999929687, "children": { "RLTrainer._checkpoint": { "total": 0.08173396900019725, "count": 1, "self": 0.08173396900019725 } } } } } } }