{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.7945910096168518, "min": 0.7279884219169617, "max": 1.477802038192749, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 24053.859375, "min": 21618.34375, "max": 44830.6015625, "count": 33 }, "Pyramids.Step.mean": { "value": 989888.0, "min": 29936.0, "max": 989888.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989888.0, "min": 29936.0, "max": 989888.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.177419051527977, "min": -0.09949477761983871, "max": 0.31257808208465576, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 44.70960235595703, "min": -24.077735900878906, "max": 82.83319091796875, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -9.262030601501465, "min": -9.674857139587402, "max": 0.3218729794025421, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -2334.03173828125, "min": -2476.763427734375, "max": 83.68697357177734, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06952561540605358, "min": 0.06507565919750079, "max": 0.07300530304327309, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.97335861568475, "min": 0.48709853741038595, "max": 1.039012470835587, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 21.92978182948959, "min": 4.787212734434234e-05, "max": 21.92978182948959, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 307.0169456128542, "min": 0.0006223376554764504, "max": 307.0169456128542, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.768361696292855e-06, "min": 7.768361696292855e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010875706374809997, "min": 0.00010875706374809997, "max": 0.0036090153969948993, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10258942142857144, "min": 0.10258942142857144, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4362519000000002, "min": 1.3886848, "max": 2.5690767, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026868320071428566, "min": 0.00026868320071428566, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003761564809999999, "min": 0.003761564809999999, "max": 0.12031020949, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.006236549932509661, "min": 0.006236549932509661, "max": 0.3460303246974945, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.08731169998645782, "min": 0.08731169998645782, "max": 2.4222123622894287, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 638.7441860465116, "min": 481.1774193548387, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 27466.0, "min": 16863.0, "max": 32337.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.8494883401449337, "min": -0.9999290848931959, "max": 1.2673694731320364, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 36.52799862623215, "min": -30.99780163168907, "max": 77.92439848184586, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.8494883401449337, "min": -0.9999290848931959, "max": 1.2673694731320364, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 36.52799862623215, "min": -30.99780163168907, "max": 77.92439848184586, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.042039520312797785, "min": 0.03562061621351094, "max": 6.4404986272839935, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 1.8076993734503048, "min": 1.8076993734503048, "max": 109.4884766638279, "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": "1736262948", "python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.5.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1736266466" }, "total": 3518.0058308730004, "count": 1, "self": 0.6387325229998169, "children": { "run_training.setup": { "total": 0.08458571400001347, "count": 1, "self": 0.08458571400001347 }, "TrainerController.start_learning": { "total": 3517.2825126360003, "count": 1, "self": 2.873206658946401, "children": { "TrainerController._reset_env": { "total": 3.084093101999997, "count": 1, "self": 3.084093101999997 }, "TrainerController.advance": { "total": 3511.2329150440532, "count": 63404, "self": 2.9549277619958048, "children": { "env_step": { "total": 2294.8175096110344, "count": 63404, "self": 2091.9090794200383, "children": { "SubprocessEnvManager._take_step": { "total": 201.22669548900944, "count": 63404, "self": 8.240255661963602, "children": { "TorchPolicy.evaluate": { "total": 192.98643982704584, "count": 62567, "self": 192.98643982704584 } } }, "workers": { "total": 1.6817347019866702, "count": 63404, "self": 0.0, "children": { "worker_root": { "total": 3509.0422792578947, "count": 63404, "is_parallel": true, "self": 1628.9950819799283, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0036418350000531063, "count": 1, "is_parallel": true, "self": 0.0011698420005359367, "children": { "_process_rank_one_or_two_observation": { "total": 0.0024719929995171697, "count": 8, "is_parallel": true, "self": 0.0024719929995171697 } } }, "UnityEnvironment.step": { "total": 0.10704589700003453, "count": 1, "is_parallel": true, "self": 0.0009220219999406254, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0006511740000405553, "count": 1, "is_parallel": true, "self": 0.0006511740000405553 }, "communicator.exchange": { "total": 0.1031088180000097, "count": 1, "is_parallel": true, "self": 0.1031088180000097 }, "steps_from_proto": { "total": 0.002363883000043643, "count": 1, "is_parallel": true, "self": 0.0005069949997960066, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018568880002476362, "count": 8, "is_parallel": true, "self": 0.0018568880002476362 } } } } } } }, "UnityEnvironment.step": { "total": 1880.0471972779665, "count": 63403, "is_parallel": true, "self": 55.67691683320163, "children": { "UnityEnvironment._generate_step_input": { "total": 33.45732223491541, "count": 63403, "is_parallel": true, "self": 33.45732223491541 }, "communicator.exchange": { "total": 1649.0304935789025, "count": 63403, "is_parallel": true, "self": 1649.0304935789025 }, "steps_from_proto": { "total": 141.88246463094697, "count": 63403, "is_parallel": true, "self": 31.425059455740666, "children": { "_process_rank_one_or_two_observation": { "total": 110.4574051752063, "count": 507224, "is_parallel": true, "self": 110.4574051752063 } } } } } } } } } } }, "trainer_advance": { "total": 1213.460477671023, "count": 63404, "self": 5.657545483058584, "children": { "process_trajectory": { "total": 195.57201219895865, "count": 63404, "self": 195.25629988395917, "children": { "RLTrainer._checkpoint": { "total": 0.31571231499947316, "count": 2, "self": 0.31571231499947316 } } }, "_update_policy": { "total": 1012.2309199890058, "count": 451, "self": 399.00318520610585, "children": { "TorchPPOOptimizer.update": { "total": 613.2277347828999, "count": 22758, "self": 613.2277347828999 } } } } } } }, "trainer_threads": { "total": 1.3960006981506012e-06, "count": 1, "self": 1.3960006981506012e-06 }, "TrainerController._save_models": { "total": 0.09229643500020757, "count": 1, "self": 0.0037344009997468675, "children": { "RLTrainer._checkpoint": { "total": 0.0885620340004607, "count": 1, "self": 0.0885620340004607 } } } } } } }