{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5143924951553345, "min": 0.5023782253265381, "max": 1.494323968887329, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 15546.998046875, "min": 15031.1572265625, "max": 45331.8125, "count": 33 }, "Pyramids.Step.mean": { "value": 989987.0, "min": 29952.0, "max": 989987.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989987.0, "min": 29952.0, "max": 989987.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.46740609407424927, "min": -0.10455676168203354, "max": 0.5233175754547119, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 124.33002471923828, "min": -25.198179244995117, "max": 141.81906127929688, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.01770658791065216, "min": -0.05731387063860893, "max": 0.39933425188064575, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 4.709952354431152, "min": -15.13086223602295, "max": 94.64221954345703, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06770658391798708, "min": 0.06583870771107429, "max": 0.07350269913797079, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.015598758769806, "min": 0.5145188939657955, "max": 1.0290402652753983, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.013227710613369902, "min": 0.0004937471945972507, "max": 0.01542022868497519, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.19841565920054852, "min": 0.0069124607243615105, "max": 0.21993783793974822, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.566537477853326e-06, "min": 7.566537477853326e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001134980621677999, "min": 0.0001134980621677999, "max": 0.0036327118890961, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10252214666666666, "min": 0.10252214666666666, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5378322, "min": 1.3886848, "max": 2.6109039000000003, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002619624519999999, "min": 0.0002619624519999999, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003929436779999998, "min": 0.003929436779999998, "max": 0.12110929961, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010869168676435947, "min": 0.010869168676435947, "max": 0.47818687558174133, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1630375236272812, "min": 0.15456107258796692, "max": 3.3473081588745117, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 409.231884057971, "min": 361.3658536585366, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28237.0, "min": 15984.0, "max": 33093.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5327825872362524, "min": -1.0000000521540642, "max": 1.5694096249090619, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 105.76199851930141, "min": -29.77300164848566, "max": 130.26099886745214, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5327825872362524, "min": -1.0000000521540642, "max": 1.5694096249090619, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 105.76199851930141, "min": -29.77300164848566, "max": 130.26099886745214, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04625894990285683, "min": 0.04269650720914753, "max": 9.883540781214833, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.1918675432971213, "min": 3.1918675432971213, "max": 158.13665249943733, "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": "1723363462", "python_version": "3.10.12 (main, Jul 29 2024, 16:56:48) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./ml-agents/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": "2.3.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1723365803" }, "total": 2340.741963333, "count": 1, "self": 0.5362217219999366, "children": { "run_training.setup": { "total": 0.05430095099995924, "count": 1, "self": 0.05430095099995924 }, "TrainerController.start_learning": { "total": 2340.15144066, "count": 1, "self": 1.5185288539937574, "children": { "TrainerController._reset_env": { "total": 2.1393548879998434, "count": 1, "self": 2.1393548879998434 }, "TrainerController.advance": { "total": 2336.396304371006, "count": 63692, "self": 1.6047940660059794, "children": { "env_step": { "total": 1672.5849237999723, "count": 63692, "self": 1523.2561234189704, "children": { "SubprocessEnvManager._take_step": { "total": 148.35760632403185, "count": 63692, "self": 5.262145859973543, "children": { "TorchPolicy.evaluate": { "total": 143.0954604640583, "count": 62565, "self": 143.0954604640583 } } }, "workers": { "total": 0.9711940569700346, "count": 63692, "self": 0.0, "children": { "worker_root": { "total": 2334.6043815019843, "count": 63692, "is_parallel": true, "self": 947.6677975079922, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0025336260000585753, "count": 1, "is_parallel": true, "self": 0.0007642280002073676, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017693979998512077, "count": 8, "is_parallel": true, "self": 0.0017693979998512077 } } }, "UnityEnvironment.step": { "total": 0.04964649900011864, "count": 1, "is_parallel": true, "self": 0.0006483100000878039, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00045290499997463485, "count": 1, "is_parallel": true, "self": 0.00045290499997463485 }, "communicator.exchange": { "total": 0.046765875000119195, "count": 1, "is_parallel": true, "self": 0.046765875000119195 }, "steps_from_proto": { "total": 0.0017794089999370044, "count": 1, "is_parallel": true, "self": 0.00037820199941052124, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014012070005264832, "count": 8, "is_parallel": true, "self": 0.0014012070005264832 } } } } } } }, "UnityEnvironment.step": { "total": 1386.9365839939921, "count": 63691, "is_parallel": true, "self": 35.659575632995484, "children": { "UnityEnvironment._generate_step_input": { "total": 25.182261847002792, "count": 63691, "is_parallel": true, "self": 25.182261847002792 }, "communicator.exchange": { "total": 1218.7040415280326, "count": 63691, "is_parallel": true, "self": 1218.7040415280326 }, "steps_from_proto": { "total": 107.39070498596129, "count": 63691, "is_parallel": true, "self": 22.508965693762093, "children": { "_process_rank_one_or_two_observation": { "total": 84.8817392921992, "count": 509528, "is_parallel": true, "self": 84.8817392921992 } } } } } } } } } } }, "trainer_advance": { "total": 662.2065865050279, "count": 63692, "self": 3.0002036149967353, "children": { "process_trajectory": { "total": 135.8082810220385, "count": 63692, "self": 135.5911562250385, "children": { "RLTrainer._checkpoint": { "total": 0.21712479699999676, "count": 2, "self": 0.21712479699999676 } } }, "_update_policy": { "total": 523.3981018679926, "count": 451, "self": 310.731110711037, "children": { "TorchPPOOptimizer.update": { "total": 212.66699115695565, "count": 22722, "self": 212.66699115695565 } } } } } } }, "trainer_threads": { "total": 1.027000052999938e-06, "count": 1, "self": 1.027000052999938e-06 }, "TrainerController._save_models": { "total": 0.09725152000009984, "count": 1, "self": 0.0014614689998779795, "children": { "RLTrainer._checkpoint": { "total": 0.09579005100022187, "count": 1, "self": 0.09579005100022187 } } } } } } }