{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.23056703805923462, "min": 0.21554438769817352, "max": 1.3803939819335938, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 6920.7001953125, "min": 6455.9853515625, "max": 41875.6328125, "count": 33 }, "Pyramids.Step.mean": { "value": 989901.0, "min": 29967.0, "max": 989901.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989901.0, "min": 29967.0, "max": 989901.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": -0.03088967315852642, "min": -0.10283046960830688, "max": 0.033609841018915176, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": -7.4753007888793945, "min": -24.884973526000977, "max": 7.999142169952393, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.21526242792606354, "min": 0.1929951161146164, "max": 0.40891966223716736, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 52.093505859375, "min": 46.65258026123047, "max": 98.14071655273438, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07027231264510193, "min": 0.06443057892592771, "max": 0.07227344747097296, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.054084689676529, "min": 0.5630178394933185, "max": 1.0675100864381437, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.0035873032350638018, "min": 0.0002971298761110097, "max": 0.00925455163416965, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.05380954852595703, "min": 0.004159818265554135, "max": 0.0740364130733572, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.467177510973333e-06, "min": 7.467177510973333e-06, "max": 0.0002948466392177875, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001120076626646, "min": 0.0001120076626646, "max": 0.0036337993887336, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10248902666666668, "min": 0.10248902666666668, "max": 0.1982822125, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5373354000000001, "min": 1.4781241999999999, "max": 2.6112664000000003, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.000258653764, "min": 0.000258653764, "max": 0.00982839302875, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.00387980646, "min": 0.00387980646, "max": 0.12114551336000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.2091526985168457, "min": 0.18660542368888855, "max": 0.5897799730300903, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 3.1372904777526855, "min": 2.4639289379119873, "max": 4.718239784240723, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 912.4193548387096, "min": 904.7941176470588, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28285.0, "min": 16637.0, "max": 32913.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": -0.41557505005039275, "min": -0.9995226312068201, "max": -0.41557505005039275, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": -13.298401601612568, "min": -30.985201567411423, "max": -12.653000891208649, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": -0.41557505005039275, "min": -0.9995226312068201, "max": -0.41557505005039275, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": -13.298401601612568, "min": -30.985201567411423, "max": -12.653000891208649, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 1.9051162272517104, "min": 1.8513291180632743, "max": 9.984047224124273, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 60.96371927205473, "min": 51.83721530577168, "max": 179.7128500342369, "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": "1679088793", "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": "1679090888" }, "total": 2094.3149930840004, "count": 1, "self": 0.5286991150001086, "children": { "run_training.setup": { "total": 0.1606932780000534, "count": 1, "self": 0.1606932780000534 }, "TrainerController.start_learning": { "total": 2093.6256006910003, "count": 1, "self": 1.5752499649811398, "children": { "TrainerController._reset_env": { "total": 6.7484651640002085, "count": 1, "self": 6.7484651640002085 }, "TrainerController.advance": { "total": 2085.208404748018, "count": 63294, "self": 1.6736964320166408, "children": { "env_step": { "total": 1457.073213867016, "count": 63294, "self": 1338.2321858289743, "children": { "SubprocessEnvManager._take_step": { "total": 117.87261510299732, "count": 63294, "self": 5.07720478506144, "children": { "TorchPolicy.evaluate": { "total": 112.79541031793588, "count": 62576, "self": 112.79541031793588 } } }, "workers": { "total": 0.9684129350443982, "count": 63294, "self": 0.0, "children": { "worker_root": { "total": 2088.5867210510173, "count": 63294, "is_parallel": true, "self": 875.1579318300574, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0026291220001439797, "count": 1, "is_parallel": true, "self": 0.000818213000002288, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018109090001416916, "count": 8, "is_parallel": true, "self": 0.0018109090001416916 } } }, "UnityEnvironment.step": { "total": 0.04597127300030479, "count": 1, "is_parallel": true, "self": 0.0005224139999882027, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004621340003723162, "count": 1, "is_parallel": true, "self": 0.0004621340003723162 }, "communicator.exchange": { "total": 0.043371590999868204, "count": 1, "is_parallel": true, "self": 0.043371590999868204 }, "steps_from_proto": { "total": 0.0016151340000760683, "count": 1, "is_parallel": true, "self": 0.0003681429998323438, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012469910002437246, "count": 8, "is_parallel": true, "self": 0.0012469910002437246 } } } } } } }, "UnityEnvironment.step": { "total": 1213.42878922096, "count": 63293, "is_parallel": true, "self": 31.47314856089679, "children": { "UnityEnvironment._generate_step_input": { "total": 23.905845628030875, "count": 63293, "is_parallel": true, "self": 23.905845628030875 }, "communicator.exchange": { "total": 1062.7324476000463, "count": 63293, "is_parallel": true, "self": 1062.7324476000463 }, "steps_from_proto": { "total": 95.31734743198604, "count": 63293, "is_parallel": true, "self": 21.16715375493868, "children": { "_process_rank_one_or_two_observation": { "total": 74.15019367704735, "count": 506344, "is_parallel": true, "self": 74.15019367704735 } } } } } } } } } } }, "trainer_advance": { "total": 626.4614944489854, "count": 63294, "self": 2.9706609380323243, "children": { "process_trajectory": { "total": 118.88685406395689, "count": 63294, "self": 118.68766139895706, "children": { "RLTrainer._checkpoint": { "total": 0.19919266499982768, "count": 2, "self": 0.19919266499982768 } } }, "_update_policy": { "total": 504.60397944699616, "count": 452, "self": 321.657853187, "children": { "TorchPPOOptimizer.update": { "total": 182.94612625999616, "count": 22686, "self": 182.94612625999616 } } } } } } }, "trainer_threads": { "total": 9.410005077370442e-07, "count": 1, "self": 9.410005077370442e-07 }, "TrainerController._save_models": { "total": 0.09347987300043314, "count": 1, "self": 0.0014255090009100968, "children": { "RLTrainer._checkpoint": { "total": 0.09205436399952305, "count": 1, "self": 0.09205436399952305 } } } } } } }