{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5115484595298767, "min": 0.5115484595298767, "max": 1.4411906003952026, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 15190.943359375, "min": 15190.943359375, "max": 43719.95703125, "count": 33 }, "Pyramids.Step.mean": { "value": 989887.0, "min": 29884.0, "max": 989887.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989887.0, "min": 29884.0, "max": 989887.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.49748340249061584, "min": -0.10632272064685822, "max": 0.5369129180908203, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 136.31045532226562, "min": -25.730098724365234, "max": 145.50340270996094, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.020441677421331406, "min": -0.020441677421331406, "max": 0.19027000665664673, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -5.601019382476807, "min": -5.601019382476807, "max": 45.855072021484375, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07035780148206479, "min": 0.06568144881773627, "max": 0.0739197281995007, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.985009220748907, "min": 0.5111037040050356, "max": 1.0286652857338434, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015497498681292026, "min": 0.0005357394663925958, "max": 0.01759607103593414, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21696498153808838, "min": 0.005988622570361422, "max": 0.24634499450307795, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.34422612338572e-06, "min": 7.34422612338572e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010281916572740008, "min": 0.00010281916572740008, "max": 0.0036337639887453993, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10244804285714286, "min": 0.10244804285714286, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4342726000000001, "min": 1.3886848, "max": 2.6112546, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002545594814285716, "min": 0.0002545594814285716, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035638327400000025, "min": 0.0035638327400000025, "max": 0.12114433454, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010327464900910854, "min": 0.010327464900910854, "max": 0.4195876121520996, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1445845067501068, "min": 0.1445845067501068, "max": 2.9371132850646973, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 361.1279069767442, "min": 351.3734939759036, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31057.0, "min": 16811.0, "max": 32295.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.522574400485948, "min": -0.9999806972280625, "max": 1.60893168518456, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 130.94139844179153, "min": -31.998801663517952, "max": 131.97159790992737, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.522574400485948, "min": -0.9999806972280625, "max": 1.60893168518456, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 130.94139844179153, "min": -31.998801663517952, "max": 131.97159790992737, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03839253804302601, "min": 0.03839253804302601, "max": 8.208896050558371, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.301758271700237, "min": 3.248090350884013, "max": 139.5512328594923, "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": "1679445516", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[GCC 9.4.0]", "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": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1679447699" }, "total": 2183.7118116400006, "count": 1, "self": 0.4882658490009817, "children": { "run_training.setup": { "total": 0.10318052299999181, "count": 1, "self": 0.10318052299999181 }, "TrainerController.start_learning": { "total": 2183.1203652679997, "count": 1, "self": 1.5774976180073281, "children": { "TrainerController._reset_env": { "total": 6.01281816300002, "count": 1, "self": 6.01281816300002 }, "TrainerController.advance": { "total": 2175.436307870993, "count": 63755, "self": 1.6990892189119222, "children": { "env_step": { "total": 1545.7246348000092, "count": 63755, "self": 1429.376456696989, "children": { "SubprocessEnvManager._take_step": { "total": 115.42046801496554, "count": 63755, "self": 5.06567333904286, "children": { "TorchPolicy.evaluate": { "total": 110.35479467592268, "count": 62569, "self": 110.35479467592268 } } }, "workers": { "total": 0.9277100880547096, "count": 63755, "self": 0.0, "children": { "worker_root": { "total": 2178.0159510420344, "count": 63755, "is_parallel": true, "self": 871.3969602400014, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018458560000453872, "count": 1, "is_parallel": true, "self": 0.0006405530002666637, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012053029997787235, "count": 8, "is_parallel": true, "self": 0.0012053029997787235 } } }, "UnityEnvironment.step": { "total": 0.04818166800009749, "count": 1, "is_parallel": true, "self": 0.000515725000468592, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00046828799986542435, "count": 1, "is_parallel": true, "self": 0.00046828799986542435 }, "communicator.exchange": { "total": 0.045495317999893814, "count": 1, "is_parallel": true, "self": 0.045495317999893814 }, "steps_from_proto": { "total": 0.001702336999869658, "count": 1, "is_parallel": true, "self": 0.000359248999529882, "children": { "_process_rank_one_or_two_observation": { "total": 0.001343088000339776, "count": 8, "is_parallel": true, "self": 0.001343088000339776 } } } } } } }, "UnityEnvironment.step": { "total": 1306.618990802033, "count": 63754, "is_parallel": true, "self": 31.829001440014963, "children": { "UnityEnvironment._generate_step_input": { "total": 23.31498287605359, "count": 63754, "is_parallel": true, "self": 23.31498287605359 }, "communicator.exchange": { "total": 1157.2193532640106, "count": 63754, "is_parallel": true, "self": 1157.2193532640106 }, "steps_from_proto": { "total": 94.25565322195393, "count": 63754, "is_parallel": true, "self": 20.561068945242596, "children": { "_process_rank_one_or_two_observation": { "total": 73.69458427671134, "count": 510032, "is_parallel": true, "self": 73.69458427671134 } } } } } } } } } } }, "trainer_advance": { "total": 628.0125838520719, "count": 63755, "self": 2.8714401650099717, "children": { "process_trajectory": { "total": 118.24235097605697, "count": 63755, "self": 118.02817149705697, "children": { "RLTrainer._checkpoint": { "total": 0.2141794789999949, "count": 2, "self": 0.2141794789999949 } } }, "_update_policy": { "total": 506.89879271100494, "count": 449, "self": 322.0582127419823, "children": { "TorchPPOOptimizer.update": { "total": 184.84057996902266, "count": 22836, "self": 184.84057996902266 } } } } } } }, "trainer_threads": { "total": 1.3359995136852376e-06, "count": 1, "self": 1.3359995136852376e-06 }, "TrainerController._save_models": { "total": 0.09374028000002, "count": 1, "self": 0.001492276999670139, "children": { "RLTrainer._checkpoint": { "total": 0.09224800300034985, "count": 1, "self": 0.09224800300034985 } } } } } } }