{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.428602933883667, "min": 0.4240873456001282, "max": 1.4388667345046997, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 12906.091796875, "min": 12688.693359375, "max": 43649.4609375, "count": 33 }, "Pyramids.Step.mean": { "value": 989970.0, "min": 29952.0, "max": 989970.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989970.0, "min": 29952.0, "max": 989970.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5296725630760193, "min": -0.11762659251689911, "max": 0.5977739691734314, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 144.07093811035156, "min": -28.465635299682617, "max": 170.36558532714844, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.007292655762284994, "min": -0.007292655762284994, "max": 0.3651055097579956, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -1.9836024045944214, "min": -1.9836024045944214, "max": 88.35552978515625, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06946116828099441, "min": 0.06611923583093848, "max": 0.07254277574496326, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0419175242149161, "min": 0.4736866809885371, "max": 1.0646841762109214, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.017217376264302194, "min": 0.000491823542535466, "max": 0.01770960290256577, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2582606439645329, "min": 0.005410058967890126, "max": 0.2582606439645329, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.587457470880002e-06, "min": 7.587457470880002e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011381186206320002, "min": 0.00011381186206320002, "max": 0.0036331411889529994, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10252912000000002, "min": 0.10252912000000002, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5379368000000002, "min": 1.3886848, "max": 2.6110469999999997, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002626590880000001, "min": 0.0002626590880000001, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003939886320000001, "min": 0.003939886320000001, "max": 0.12112359530000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.014557884074747562, "min": 0.014557884074747562, "max": 0.49442628026008606, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.218368262052536, "min": 0.20432652533054352, "max": 3.460983991622925, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 363.2564102564103, "min": 308.8556701030928, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28334.0, "min": 15984.0, "max": 32316.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5854512565793135, "min": -1.0000000521540642, "max": 1.6499030748286199, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 123.66519801318645, "min": -31.997201651334763, "max": 160.04059825837612, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5854512565793135, "min": -1.0000000521540642, "max": 1.6499030748286199, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 123.66519801318645, "min": -31.997201651334763, "max": 160.04059825837612, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.054531377216335386, "min": 0.05044994874468515, "max": 10.087773490697145, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.25344742287416, "min": 4.25344742287416, "max": 161.40437585115433, "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": "1700155026", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "2.1.0+cu118", "numpy_version": "1.23.5", "end_time_seconds": "1700157421" }, "total": 2394.462917179, "count": 1, "self": 0.47672261400020943, "children": { "run_training.setup": { "total": 0.04562203199998294, "count": 1, "self": 0.04562203199998294 }, "TrainerController.start_learning": { "total": 2393.9405725330002, "count": 1, "self": 1.6336691000274186, "children": { "TrainerController._reset_env": { "total": 4.573602327999879, "count": 1, "self": 4.573602327999879 }, "TrainerController.advance": { "total": 2387.6498104919724, "count": 63931, "self": 1.7738278268316208, "children": { "env_step": { "total": 1728.7174099060971, "count": 63931, "self": 1579.7855124230505, "children": { "SubprocessEnvManager._take_step": { "total": 147.91372851701226, "count": 63931, "self": 5.1241297769854555, "children": { "TorchPolicy.evaluate": { "total": 142.7895987400268, "count": 62563, "self": 142.7895987400268 } } }, "workers": { "total": 1.018168966034409, "count": 63931, "self": 0.0, "children": { "worker_root": { "total": 2388.6713924379565, "count": 63931, "is_parallel": true, "self": 939.156370706047, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0019086770000740216, "count": 1, "is_parallel": true, "self": 0.0006004250001296896, "children": { "_process_rank_one_or_two_observation": { "total": 0.001308251999944332, "count": 8, "is_parallel": true, "self": 0.001308251999944332 } } }, "UnityEnvironment.step": { "total": 0.08896567900001173, "count": 1, "is_parallel": true, "self": 0.0005596610001248337, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005038300000705931, "count": 1, "is_parallel": true, "self": 0.0005038300000705931 }, "communicator.exchange": { "total": 0.08623267799998757, "count": 1, "is_parallel": true, "self": 0.08623267799998757 }, "steps_from_proto": { "total": 0.0016695099998287333, "count": 1, "is_parallel": true, "self": 0.0003595539997149899, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013099560001137434, "count": 8, "is_parallel": true, "self": 0.0013099560001137434 } } } } } } }, "UnityEnvironment.step": { "total": 1449.5150217319094, "count": 63930, "is_parallel": true, "self": 36.06239119688098, "children": { "UnityEnvironment._generate_step_input": { "total": 24.25869536602886, "count": 63930, "is_parallel": true, "self": 24.25869536602886 }, "communicator.exchange": { "total": 1287.5401344009586, "count": 63930, "is_parallel": true, "self": 1287.5401344009586 }, "steps_from_proto": { "total": 101.65380076804104, "count": 63930, "is_parallel": true, "self": 21.33768137311131, "children": { "_process_rank_one_or_two_observation": { "total": 80.31611939492973, "count": 511440, "is_parallel": true, "self": 80.31611939492973 } } } } } } } } } } }, "trainer_advance": { "total": 657.1585727590436, "count": 63931, "self": 3.1148075160595, "children": { "process_trajectory": { "total": 126.86145943998463, "count": 63931, "self": 126.69525581998505, "children": { "RLTrainer._checkpoint": { "total": 0.16620361999957822, "count": 2, "self": 0.16620361999957822 } } }, "_update_policy": { "total": 527.1823058029995, "count": 454, "self": 316.2655701059905, "children": { "TorchPPOOptimizer.update": { "total": 210.91673569700902, "count": 22794, "self": 210.91673569700902 } } } } } } }, "trainer_threads": { "total": 1.2710006558336318e-06, "count": 1, "self": 1.2710006558336318e-06 }, "TrainerController._save_models": { "total": 0.08348934199966607, "count": 1, "self": 0.0015438289992744103, "children": { "RLTrainer._checkpoint": { "total": 0.08194551300039166, "count": 1, "self": 0.08194551300039166 } } } } } } }