{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.6002390384674072, "min": 0.6002390384674072, "max": 1.5111905336380005, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 18064.794921875, "min": 18055.84375, "max": 45843.4765625, "count": 33 }, "Pyramids.Step.mean": { "value": 989874.0, "min": 29952.0, "max": 989874.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989874.0, "min": 29952.0, "max": 989874.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.421282023191452, "min": -0.1012439876794815, "max": 0.421282023191452, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 113.32486724853516, "min": -24.29855728149414, "max": 113.32486724853516, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.19381114840507507, "min": -0.10473549365997314, "max": 0.22029291093349457, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 52.13520050048828, "min": -27.545434951782227, "max": 53.09059143066406, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06652911262478614, "min": 0.06548174557974562, "max": 0.07360878979804626, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9314075767470059, "min": 0.5152615285863238, "max": 1.040516691790282, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014733827552325756, "min": 0.00011535945954258354, "max": 0.016209029710395242, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.20627358573256058, "min": 0.0014996729740535861, "max": 0.2269264159455334, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.670261728992862e-06, "min": 7.670261728992862e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010738366420590006, "min": 0.00010738366420590006, "max": 0.003377212974262399, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10255672142857143, "min": 0.10255672142857143, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4357941, "min": 1.3886848, "max": 2.4257375999999997, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002654164707142859, "min": 0.0002654164707142859, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0037158305900000027, "min": 0.0037158305900000027, "max": 0.11259118623999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.011788549832999706, "min": 0.011315928772091866, "max": 0.4035390317440033, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.16503970324993134, "min": 0.15842300653457642, "max": 2.8247733116149902, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 432.07042253521126, "min": 432.07042253521126, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30677.0, "min": 15984.0, "max": 32920.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.3988619431013791, "min": -1.0000000521540642, "max": 1.3988619431013791, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 99.31919796019793, "min": -30.99280158430338, "max": 99.31919796019793, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.3988619431013791, "min": -1.0000000521540642, "max": 1.3988619431013791, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 99.31919796019793, "min": -30.99280158430338, "max": 99.31919796019793, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.05155483815732124, "min": 0.05155483815732124, "max": 8.259709045290947, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.6603935091698077, "min": 3.4257656136032892, "max": 132.15534472465515, "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": "1717829806", "python_version": "3.10.14 (main, Mar 21 2024, 16:24:04) [GCC 11.2.0]", "command_line_arguments": "/home/raghu/anaconda3/envs/rl/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": "1717830545" }, "total": 738.5612768740002, "count": 1, "self": 0.21800393800003803, "children": { "run_training.setup": { "total": 0.011884528000337014, "count": 1, "self": 0.011884528000337014 }, "TrainerController.start_learning": { "total": 738.3313884079998, "count": 1, "self": 0.7258146980320817, "children": { "TrainerController._reset_env": { "total": 1.2320824019998327, "count": 1, "self": 1.2320824019998327 }, "TrainerController.advance": { "total": 736.319174680968, "count": 63449, "self": 0.6114971828519629, "children": { "env_step": { "total": 473.07639561900487, "count": 63449, "self": 414.3297357061656, "children": { "SubprocessEnvManager._take_step": { "total": 58.24589287681647, "count": 63449, "self": 1.8598405257616832, "children": { "TorchPolicy.evaluate": { "total": 56.386052351054786, "count": 62563, "self": 56.386052351054786 } } }, "workers": { "total": 0.5007670360228076, "count": 63449, "self": 0.0, "children": { "worker_root": { "total": 737.2578054539717, "count": 63449, "is_parallel": true, "self": 371.85457649701493, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0008918510002331459, "count": 1, "is_parallel": true, "self": 0.00024807399950077524, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006437770007323707, "count": 8, "is_parallel": true, "self": 0.0006437770007323707 } } }, "UnityEnvironment.step": { "total": 0.01586760400005005, "count": 1, "is_parallel": true, "self": 0.00016921699989325134, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00027782000051956857, "count": 1, "is_parallel": true, "self": 0.00027782000051956857 }, "communicator.exchange": { "total": 0.014972746999774245, "count": 1, "is_parallel": true, "self": 0.014972746999774245 }, "steps_from_proto": { "total": 0.00044781999986298615, "count": 1, "is_parallel": true, "self": 0.00010933300109172706, "children": { "_process_rank_one_or_two_observation": { "total": 0.0003384869987712591, "count": 8, "is_parallel": true, "self": 0.0003384869987712591 } } } } } } }, "UnityEnvironment.step": { "total": 365.4032289569568, "count": 63448, "is_parallel": true, "self": 12.455523446157713, "children": { "UnityEnvironment._generate_step_input": { "total": 8.401065171978189, "count": 63448, "is_parallel": true, "self": 8.401065171978189 }, "communicator.exchange": { "total": 307.1716708649201, "count": 63448, "is_parallel": true, "self": 307.1716708649201 }, "steps_from_proto": { "total": 37.37496947390082, "count": 63448, "is_parallel": true, "self": 7.703178046732319, "children": { "_process_rank_one_or_two_observation": { "total": 29.6717914271685, "count": 507584, "is_parallel": true, "self": 29.6717914271685 } } } } } } } } } } }, "trainer_advance": { "total": 262.63128187911116, "count": 63449, "self": 1.4036027959473358, "children": { "process_trajectory": { "total": 51.145792480147975, "count": 63449, "self": 51.0368584041471, "children": { "RLTrainer._checkpoint": { "total": 0.10893407600087812, "count": 2, "self": 0.10893407600087812 } } }, "_update_policy": { "total": 210.08188660301585, "count": 445, "self": 123.34318368299228, "children": { "TorchPPOOptimizer.update": { "total": 86.73870292002357, "count": 22782, "self": 86.73870292002357 } } } } } } }, "trainer_threads": { "total": 5.609999789157882e-07, "count": 1, "self": 5.609999789157882e-07 }, "TrainerController._save_models": { "total": 0.054316065999955754, "count": 1, "self": 0.0014151630002743332, "children": { "RLTrainer._checkpoint": { "total": 0.05290090299968142, "count": 1, "self": 0.05290090299968142 } } } } } } }