{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5889737606048584, "min": 0.5854454636573792, "max": 1.4055655002593994, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 17697.484375, "min": 17647.66796875, "max": 42639.234375, "count": 33 }, "Pyramids.Step.mean": { "value": 989900.0, "min": 29952.0, "max": 989900.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989900.0, "min": 29952.0, "max": 989900.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.18668167293071747, "min": -0.106877401471138, "max": 0.1946895718574524, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 47.97718811035156, "min": -25.75745391845703, "max": 49.45115280151367, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.44912707805633545, "min": -0.11661994457244873, "max": 0.7304412126541138, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 115.4256591796875, "min": -29.6214656829834, "max": 173.11456298828125, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06829019276511983, "min": 0.06567004802456636, "max": 0.07319228416644637, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9560626987116776, "min": 0.5009770855302895, "max": 1.0604173963074572, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.0505443668182267, "min": 0.00020144575900598848, "max": 0.0505443668182267, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.7076211354551738, "min": 0.0028202406260838388, "max": 0.7076211354551738, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.422654668671433e-06, "min": 7.422654668671433e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010391716536140007, "min": 0.00010391716536140007, "max": 0.0035076614307796, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10247418571428572, "min": 0.10247418571428572, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4346386000000002, "min": 1.3886848, "max": 2.5692204, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025717115285714306, "min": 0.00025717115285714306, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036003961400000025, "min": 0.0036003961400000025, "max": 0.11694511796, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.016612287610769272, "min": 0.016435718163847923, "max": 0.6745191812515259, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.2325720191001892, "min": 0.23024119436740875, "max": 4.721634387969971, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 584.6153846153846, "min": 584.6153846153846, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30400.0, "min": 15984.0, "max": 33097.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.8767692021165903, "min": -1.0000000521540642, "max": 0.8767692021165903, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 45.591998510062695, "min": -30.745801769196987, "max": 45.591998510062695, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.8767692021165903, "min": -1.0000000521540642, "max": 0.8767692021165903, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 45.591998510062695, "min": -30.745801769196987, "max": 45.591998510062695, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.09984455910531463, "min": 0.09984455910531463, "max": 14.22121711447835, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 5.191917073476361, "min": 4.786510685284156, "max": 227.5394738316536, "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": "1689436279", "python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [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": "1689438506" }, "total": 2226.8685961970004, "count": 1, "self": 0.4826569270003347, "children": { "run_training.setup": { "total": 0.03862324399995032, "count": 1, "self": 0.03862324399995032 }, "TrainerController.start_learning": { "total": 2226.347316026, "count": 1, "self": 1.482592812067196, "children": { "TrainerController._reset_env": { "total": 4.151113783000028, "count": 1, "self": 4.151113783000028 }, "TrainerController.advance": { "total": 2220.6222812849333, "count": 63393, "self": 1.5100999339656482, "children": { "env_step": { "total": 1550.4962126359728, "count": 63393, "self": 1434.4200713579048, "children": { "SubprocessEnvManager._take_step": { "total": 115.2016280210388, "count": 63393, "self": 4.853687228083459, "children": { "TorchPolicy.evaluate": { "total": 110.34794079295534, "count": 62572, "self": 110.34794079295534 } } }, "workers": { "total": 0.8745132570293208, "count": 63393, "self": 0.0, "children": { "worker_root": { "total": 2221.195639222984, "count": 63393, "is_parallel": true, "self": 903.4703006380473, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018957739999905243, "count": 1, "is_parallel": true, "self": 0.00057146099993588, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013243130000546444, "count": 8, "is_parallel": true, "self": 0.0013243130000546444 } } }, "UnityEnvironment.step": { "total": 0.054198573000007855, "count": 1, "is_parallel": true, "self": 0.0006718600001249797, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005106369999339222, "count": 1, "is_parallel": true, "self": 0.0005106369999339222 }, "communicator.exchange": { "total": 0.05075729999998657, "count": 1, "is_parallel": true, "self": 0.05075729999998657 }, "steps_from_proto": { "total": 0.0022587759999623813, "count": 1, "is_parallel": true, "self": 0.0004113810000490048, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018473949999133765, "count": 8, "is_parallel": true, "self": 0.0018473949999133765 } } } } } } }, "UnityEnvironment.step": { "total": 1317.7253385849367, "count": 63392, "is_parallel": true, "self": 34.60739540290888, "children": { "UnityEnvironment._generate_step_input": { "total": 23.06231559100445, "count": 63392, "is_parallel": true, "self": 23.06231559100445 }, "communicator.exchange": { "total": 1153.3920841130057, "count": 63392, "is_parallel": true, "self": 1153.3920841130057 }, "steps_from_proto": { "total": 106.66354347801769, "count": 63392, "is_parallel": true, "self": 20.731451548112318, "children": { "_process_rank_one_or_two_observation": { "total": 85.93209192990537, "count": 507136, "is_parallel": true, "self": 85.93209192990537 } } } } } } } } } } }, "trainer_advance": { "total": 668.6159687149947, "count": 63393, "self": 2.819989432982993, "children": { "process_trajectory": { "total": 110.31504068801155, "count": 63393, "self": 110.10727649301157, "children": { "RLTrainer._checkpoint": { "total": 0.20776419499998156, "count": 2, "self": 0.20776419499998156 } } }, "_update_policy": { "total": 555.4809385940001, "count": 451, "self": 360.854777838994, "children": { "TorchPPOOptimizer.update": { "total": 194.62616075500614, "count": 22797, "self": 194.62616075500614 } } } } } } }, "trainer_threads": { "total": 1.008999788609799e-06, "count": 1, "self": 1.008999788609799e-06 }, "TrainerController._save_models": { "total": 0.0913271370000075, "count": 1, "self": 0.001367839000067761, "children": { "RLTrainer._checkpoint": { "total": 0.08995929799993974, "count": 1, "self": 0.08995929799993974 } } } } } } }