{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3598055839538574, "min": 0.3598055839538574, "max": 1.5309752225875854, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 10851.736328125, "min": 10851.736328125, "max": 46443.6640625, "count": 33 }, "Pyramids.Step.mean": { "value": 989896.0, "min": 29994.0, "max": 989896.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989896.0, "min": 29994.0, "max": 989896.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5539183616638184, "min": -0.2961362898349762, "max": 0.5958210825920105, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 150.66580200195312, "min": -70.48043823242188, "max": 166.2340850830078, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.02045316994190216, "min": -0.010399440303444862, "max": 0.25156673789024353, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 5.563261985778809, "min": -2.8494465351104736, "max": 60.376014709472656, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06867536004990273, "min": 0.06587541749606664, "max": 0.07573059020208384, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9614550406986382, "min": 0.4874452137101934, "max": 1.0716466488859926, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.012615489383495602, "min": 0.000991551212830523, "max": 0.016523123476912992, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.17661685136893843, "min": 0.011898614553966276, "max": 0.2478468521536949, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.510876067835712e-06, "min": 7.510876067835712e-06, "max": 0.00029523660158779996, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010515226494969997, "min": 0.00010515226494969997, "max": 0.0036326344891218997, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10250359285714285, "min": 0.10250359285714285, "max": 0.19841219999999998, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4350503, "min": 1.3888854, "max": 2.6108781000000003, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002601089264285714, "min": 0.0002601089264285714, "max": 0.009841378779999998, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036415249699999997, "min": 0.0036415249699999997, "max": 0.12110672219000002, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010944602079689503, "min": 0.010944602079689503, "max": 0.27505427598953247, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1532244235277176, "min": 0.1532244235277176, "max": 1.925379991531372, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 361.8101265822785, "min": 314.7263157894737, "max": 995.53125, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28583.0, "min": 16665.0, "max": 32731.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.536898720019226, "min": -0.9339625516440719, "max": 1.6338694490100207, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 121.41499888151884, "min": -29.886801652610302, "max": 155.21759765595198, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.536898720019226, "min": -0.9339625516440719, "max": 1.6338694490100207, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 121.41499888151884, "min": -29.886801652610302, "max": 155.21759765595198, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04160521712479818, "min": 0.03934938177178418, "max": 5.143943631911979, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.2868121528590564, "min": 3.2868121528590564, "max": 87.44704174250364, "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": "1709185918", "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": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1709188206" }, "total": 2287.722922597, "count": 1, "self": 0.4931524279995756, "children": { "run_training.setup": { "total": 0.048639763000096536, "count": 1, "self": 0.048639763000096536 }, "TrainerController.start_learning": { "total": 2287.181130406, "count": 1, "self": 1.4166534210207828, "children": { "TrainerController._reset_env": { "total": 3.083619581999983, "count": 1, "self": 3.083619581999983 }, "TrainerController.advance": { "total": 2282.59406352598, "count": 63994, "self": 1.572455110041119, "children": { "env_step": { "total": 1646.27091805001, "count": 63994, "self": 1508.9713378180693, "children": { "SubprocessEnvManager._take_step": { "total": 136.41079196696705, "count": 63994, "self": 4.987529370929678, "children": { "TorchPolicy.evaluate": { "total": 131.42326259603738, "count": 62560, "self": 131.42326259603738 } } }, "workers": { "total": 0.8887882649737548, "count": 63994, "self": 0.0, "children": { "worker_root": { "total": 2281.6531553690456, "count": 63994, "is_parallel": true, "self": 896.9713200880174, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005466053000077409, "count": 1, "is_parallel": true, "self": 0.003914527000006274, "children": { "_process_rank_one_or_two_observation": { "total": 0.001551526000071135, "count": 8, "is_parallel": true, "self": 0.001551526000071135 } } }, "UnityEnvironment.step": { "total": 0.05402123900000788, "count": 1, "is_parallel": true, "self": 0.0006603520000680874, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005316149999998743, "count": 1, "is_parallel": true, "self": 0.0005316149999998743 }, "communicator.exchange": { "total": 0.051136541999994733, "count": 1, "is_parallel": true, "self": 0.051136541999994733 }, "steps_from_proto": { "total": 0.0016927299999451861, "count": 1, "is_parallel": true, "self": 0.00038890299970262276, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013038270002425634, "count": 8, "is_parallel": true, "self": 0.0013038270002425634 } } } } } } }, "UnityEnvironment.step": { "total": 1384.6818352810283, "count": 63993, "is_parallel": true, "self": 37.468755719952924, "children": { "UnityEnvironment._generate_step_input": { "total": 27.02364758606393, "count": 63993, "is_parallel": true, "self": 27.02364758606393 }, "communicator.exchange": { "total": 1210.9004475190313, "count": 63993, "is_parallel": true, "self": 1210.9004475190313 }, "steps_from_proto": { "total": 109.2889844559802, "count": 63993, "is_parallel": true, "self": 22.27704500902837, "children": { "_process_rank_one_or_two_observation": { "total": 87.01193944695183, "count": 511944, "is_parallel": true, "self": 87.01193944695183 } } } } } } } } } } }, "trainer_advance": { "total": 634.7506903659287, "count": 63994, "self": 2.8303624399846967, "children": { "process_trajectory": { "total": 130.91280017694544, "count": 63994, "self": 130.7165028959455, "children": { "RLTrainer._checkpoint": { "total": 0.1962972809999428, "count": 2, "self": 0.1962972809999428 } } }, "_update_policy": { "total": 501.00752774899854, "count": 456, "self": 294.68931625600703, "children": { "TorchPPOOptimizer.update": { "total": 206.3182114929915, "count": 22803, "self": 206.3182114929915 } } } } } } }, "trainer_threads": { "total": 1.2819996300095227e-06, "count": 1, "self": 1.2819996300095227e-06 }, "TrainerController._save_models": { "total": 0.08679259500013359, "count": 1, "self": 0.0014132800001789292, "children": { "RLTrainer._checkpoint": { "total": 0.08537931499995466, "count": 1, "self": 0.08537931499995466 } } } } } } }