{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.26119568943977356, "min": 0.26099422574043274, "max": 1.4298911094665527, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 7781.5419921875, "min": 7781.5419921875, "max": 43377.17578125, "count": 33 }, "Pyramids.Step.mean": { "value": 989967.0, "min": 29951.0, "max": 989967.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989967.0, "min": 29951.0, "max": 989967.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6369694471359253, "min": -0.06746885180473328, "max": 0.7133278846740723, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 180.26235961914062, "min": -16.192523956298828, "max": 203.29844665527344, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.042019348591566086, "min": 0.039504799991846085, "max": 0.43181222677230835, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 11.891475677490234, "min": 11.123594284057617, "max": 103.203125, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07159924177966193, "min": 0.06525118655092965, "max": 0.07457467446719031, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.002389384915267, "min": 0.5767807592028441, "max": 1.0984150302777862, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01631382437696301, "min": 0.0018620471985934884, "max": 0.017473291421386723, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.22839354127748213, "min": 0.024206613581715348, "max": 0.24462607989941412, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.410354672771428e-06, "min": 7.410354672771428e-06, "max": 0.00029492325169225004, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010374496541879999, "min": 0.00010374496541879999, "max": 0.0037579975473341996, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10247008571428573, "min": 0.10247008571428573, "max": 0.19830775, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4345812000000002, "min": 1.4345812000000002, "max": 2.6526658000000003, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002567615628571429, "min": 0.0002567615628571429, "max": 0.009830944224999999, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035946618800000003, "min": 0.0035946618800000003, "max": 0.12528131341999998, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.04930257052183151, "min": 0.04930257052183151, "max": 0.5915135145187378, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.69023597240448, "min": 0.69023597240448, "max": 4.732108116149902, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 296.75728155339806, "min": 276.49038461538464, "max": 973.8125, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30566.0, "min": 17004.0, "max": 32223.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6449786224990215, "min": -0.7870938044507056, "max": 1.7042749826438153, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 169.43279811739922, "min": -25.18700174242258, "max": 177.91879756748676, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6449786224990215, "min": -0.7870938044507056, "max": 1.7042749826438153, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 169.43279811739922, "min": -25.18700174242258, "max": 177.91879756748676, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.1481886815016375, "min": 0.1430048355575239, "max": 10.747816481284405, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 15.263434194668662, "min": 14.872502897982486, "max": 204.2085131444037, "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": "1704037189", "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": "2.1.2+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1704039540" }, "total": 2350.9530069459997, "count": 1, "self": 0.49090271800014307, "children": { "run_training.setup": { "total": 0.07898913099984384, "count": 1, "self": 0.07898913099984384 }, "TrainerController.start_learning": { "total": 2350.383115097, "count": 1, "self": 1.3940879319457053, "children": { "TrainerController._reset_env": { "total": 2.7792991049998363, "count": 1, "self": 2.7792991049998363 }, "TrainerController.advance": { "total": 2346.122653655054, "count": 64149, "self": 1.4692011260553954, "children": { "env_step": { "total": 1699.5210172450163, "count": 64149, "self": 1570.3349881129416, "children": { "SubprocessEnvManager._take_step": { "total": 128.31026739908498, "count": 64149, "self": 4.742903240089845, "children": { "TorchPolicy.evaluate": { "total": 123.56736415899513, "count": 62562, "self": 123.56736415899513 } } }, "workers": { "total": 0.8757617329897585, "count": 64149, "self": 0.0, "children": { "worker_root": { "total": 2345.060134105058, "count": 64149, "is_parallel": true, "self": 898.2047766810783, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0023354959998869163, "count": 1, "is_parallel": true, "self": 0.0005874180001228524, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017480779997640639, "count": 8, "is_parallel": true, "self": 0.0017480779997640639 } } }, "UnityEnvironment.step": { "total": 0.05326069199986705, "count": 1, "is_parallel": true, "self": 0.000579647999984445, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00045306699985303567, "count": 1, "is_parallel": true, "self": 0.00045306699985303567 }, "communicator.exchange": { "total": 0.05050493700014158, "count": 1, "is_parallel": true, "self": 0.05050493700014158 }, "steps_from_proto": { "total": 0.0017230399998879875, "count": 1, "is_parallel": true, "self": 0.000361898999699406, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013611410001885815, "count": 8, "is_parallel": true, "self": 0.0013611410001885815 } } } } } } }, "UnityEnvironment.step": { "total": 1446.8553574239795, "count": 64148, "is_parallel": true, "self": 35.91156063404628, "children": { "UnityEnvironment._generate_step_input": { "total": 24.65688186500779, "count": 64148, "is_parallel": true, "self": 24.65688186500779 }, "communicator.exchange": { "total": 1285.5161713969007, "count": 64148, "is_parallel": true, "self": 1285.5161713969007 }, "steps_from_proto": { "total": 100.7707435280247, "count": 64148, "is_parallel": true, "self": 20.075494483008015, "children": { "_process_rank_one_or_two_observation": { "total": 80.69524904501668, "count": 513184, "is_parallel": true, "self": 80.69524904501668 } } } } } } } } } } }, "trainer_advance": { "total": 645.1324352839822, "count": 64149, "self": 2.71595315191189, "children": { "process_trajectory": { "total": 130.158476508072, "count": 64149, "self": 129.96308365007235, "children": { "RLTrainer._checkpoint": { "total": 0.19539285799965, "count": 2, "self": 0.19539285799965 } } }, "_update_policy": { "total": 512.2580056239983, "count": 460, "self": 305.13415274900103, "children": { "TorchPPOOptimizer.update": { "total": 207.12385287499728, "count": 22752, "self": 207.12385287499728 } } } } } } }, "trainer_threads": { "total": 8.950000847107731e-07, "count": 1, "self": 8.950000847107731e-07 }, "TrainerController._save_models": { "total": 0.08707351000020935, "count": 1, "self": 0.0014268130003074475, "children": { "RLTrainer._checkpoint": { "total": 0.0856466969999019, "count": 1, "self": 0.0856466969999019 } } } } } } }