{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.16923873126506805, "min": 0.15387769043445587, "max": 1.392237663269043, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 5063.623046875, "min": 4623.716796875, "max": 42234.921875, "count": 100 }, "Pyramids.Step.mean": { "value": 2999900.0, "min": 29919.0, "max": 2999900.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999900.0, "min": 29919.0, "max": 2999900.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.7073608040809631, "min": -0.1038007065653801, "max": 0.8387097120285034, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 204.42727661132812, "min": -24.91217041015625, "max": 257.48388671875, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.001167872454971075, "min": -0.03060208447277546, "max": 0.5459747910499573, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -0.3375151455402374, "min": -8.170756340026855, "max": 129.39602661132812, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06686581841980417, "min": 0.06425255079779568, "max": 0.07471496330496545, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9361214578772583, "min": 0.5211475720204582, "max": 1.1207244495744817, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015319574728242257, "min": 0.0005170813444722865, "max": 0.016436001453807914, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2144740461953916, "min": 0.007239138822612011, "max": 0.24113307990574318, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.427028095785715e-06, "min": 1.427028095785715e-06, "max": 0.0002984114433866619, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 1.997839334100001e-05, "min": 1.997839334100001e-05, "max": 0.0040534803488399, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10047564285714285, "min": 0.10047564285714285, "max": 0.19947048095238099, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4066589999999999, "min": 1.3962933666666668, "max": 2.767598466666667, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 5.751672142857146e-05, "min": 5.751672142857146e-05, "max": 0.009947101047142857, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.0008052341000000004, "min": 0.0008052341000000004, "max": 0.13512089399, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.003657291177660227, "min": 0.0035110157914459705, "max": 0.6255466341972351, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.05120207741856575, "min": 0.04915422201156616, "max": 4.37882661819458, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 270.33613445378154, "min": 215.4558823529412, "max": 995.75, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 32170.0, "min": 16590.0, "max": 33514.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6456134298018046, "min": -0.9011714799063546, "max": 1.7705624867230654, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 195.82799814641476, "min": -27.88520162552595, "max": 246.80839815735817, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6456134298018046, "min": -0.9011714799063546, "max": 1.7705624867230654, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 195.82799814641476, "min": -27.88520162552595, "max": 246.80839815735817, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.010227753245357341, "min": 0.008490495279716015, "max": 12.811901366009431, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 1.2171026361975237, "min": 1.0723469940166979, "max": 217.80232322216034, "count": 100 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1682366045", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[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": "1682373290" }, "total": 7244.933540562, "count": 1, "self": 0.5875041170002078, "children": { "run_training.setup": { "total": 0.12015660799988837, "count": 1, "self": 0.12015660799988837 }, "TrainerController.start_learning": { "total": 7244.225879837, "count": 1, "self": 4.3835416131269085, "children": { "TrainerController._reset_env": { "total": 4.880979290000141, "count": 1, "self": 4.880979290000141 }, "TrainerController.advance": { "total": 7234.855575078875, "count": 194855, "self": 4.465410740527659, "children": { "env_step": { "total": 5381.861249426189, "count": 194855, "self": 5055.111160877128, "children": { "SubprocessEnvManager._take_step": { "total": 324.0444030460351, "count": 194855, "self": 14.383346056008577, "children": { "TorchPolicy.evaluate": { "total": 309.6610569900265, "count": 187554, "self": 309.6610569900265 } } }, "workers": { "total": 2.7056855030255065, "count": 194855, "self": 0.0, "children": { "worker_root": { "total": 7228.357352539032, "count": 194855, "is_parallel": true, "self": 2527.1557350461844, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017361380000693316, "count": 1, "is_parallel": true, "self": 0.0005433819997051614, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011927560003641702, "count": 8, "is_parallel": true, "self": 0.0011927560003641702 } } }, "UnityEnvironment.step": { "total": 0.0969678159999603, "count": 1, "is_parallel": true, "self": 0.0005631899998661538, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005159739998816804, "count": 1, "is_parallel": true, "self": 0.0005159739998816804 }, "communicator.exchange": { "total": 0.0941666470000655, "count": 1, "is_parallel": true, "self": 0.0941666470000655 }, "steps_from_proto": { "total": 0.0017220050001469644, "count": 1, "is_parallel": true, "self": 0.00039998999955059844, "children": { "_process_rank_one_or_two_observation": { "total": 0.001322015000596366, "count": 8, "is_parallel": true, "self": 0.001322015000596366 } } } } } } }, "UnityEnvironment.step": { "total": 4701.201617492848, "count": 194854, "is_parallel": true, "self": 98.92284734201439, "children": { "UnityEnvironment._generate_step_input": { "total": 73.68766544212394, "count": 194854, "is_parallel": true, "self": 73.68766544212394 }, "communicator.exchange": { "total": 4227.162682559855, "count": 194854, "is_parallel": true, "self": 4227.162682559855 }, "steps_from_proto": { "total": 301.4284221488547, "count": 194854, "is_parallel": true, "self": 65.12089369596492, "children": { "_process_rank_one_or_two_observation": { "total": 236.30752845288976, "count": 1558832, "is_parallel": true, "self": 236.30752845288976 } } } } } } } } } } }, "trainer_advance": { "total": 1848.528914912158, "count": 194855, "self": 8.201303023952732, "children": { "process_trajectory": { "total": 343.48472145322376, "count": 194855, "self": 342.7644949572227, "children": { "RLTrainer._checkpoint": { "total": 0.7202264960010325, "count": 6, "self": 0.7202264960010325 } } }, "_update_policy": { "total": 1496.8428904349814, "count": 1408, "self": 958.5195810991013, "children": { "TorchPPOOptimizer.update": { "total": 538.3233093358801, "count": 68379, "self": 538.3233093358801 } } } } } } }, "trainer_threads": { "total": 9.539999155094847e-07, "count": 1, "self": 9.539999155094847e-07 }, "TrainerController._save_models": { "total": 0.10578290099874721, "count": 1, "self": 0.001524700997833861, "children": { "RLTrainer._checkpoint": { "total": 0.10425820000091335, "count": 1, "self": 0.10425820000091335 } } } } } } }