{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5452258586883545, "min": 0.5272359251976013, "max": 1.5088955163955688, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 16286.986328125, "min": 15649.966796875, "max": 45773.85546875, "count": 33 }, "Pyramids.Step.mean": { "value": 989958.0, "min": 29952.0, "max": 989958.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989958.0, "min": 29952.0, "max": 989958.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5199617147445679, "min": -0.17816665768623352, "max": 0.5610929131507874, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 143.50942993164062, "min": -42.22549819946289, "max": 157.10601806640625, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.10759282112121582, "min": -0.012301337905228138, "max": 0.18525969982147217, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 29.695619583129883, "min": -3.345963954925537, "max": 44.076019287109375, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06788736575981602, "min": 0.06476004480942579, "max": 0.0725802447247718, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9504231206374243, "min": 0.4977299113829497, "max": 1.0647544749614706, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.017489469399844807, "min": 0.00010955712538939268, "max": 0.017489469399844807, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.24485257159782728, "min": 0.0013146855046727122, "max": 0.24485257159782728, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.365676116235714e-06, "min": 7.365676116235714e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001031194656273, "min": 0.0001031194656273, "max": 0.0030493248835583996, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10245519285714286, "min": 0.10245519285714286, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4343727, "min": 1.3886848, "max": 2.317283, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025527376642857147, "min": 0.00025527376642857147, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035738327300000004, "min": 0.0035738327300000004, "max": 0.10165251584, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.008032689802348614, "min": 0.008032689802348614, "max": 0.23355808854103088, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.11245766282081604, "min": 0.11245766282081604, "max": 1.6349066495895386, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 356.6511627906977, "min": 325.27906976744185, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30672.0, "min": 15984.0, "max": 32457.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6200813750714758, "min": -1.0000000521540642, "max": 1.6200813750714758, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 139.3269982561469, "min": -31.998001664876938, "max": 139.3269982561469, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6200813750714758, "min": -1.0000000521540642, "max": 1.6200813750714758, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 139.3269982561469, "min": -31.998001664876938, "max": 139.3269982561469, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.029942167345261835, "min": 0.029942167345261835, "max": 4.875790709163994, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.575026391692518, "min": 2.575026391692518, "max": 78.0126513466239, "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": "1718373863", "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": "2.3.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1718375422" }, "total": 1558.8377594610001, "count": 1, "self": 0.32207169299999805, "children": { "run_training.setup": { "total": 0.05362079499991523, "count": 1, "self": 0.05362079499991523 }, "TrainerController.start_learning": { "total": 1558.4620669730002, "count": 1, "self": 1.2501220150402332, "children": { "TrainerController._reset_env": { "total": 2.1324298460003774, "count": 1, "self": 2.1324298460003774 }, "TrainerController.advance": { "total": 1555.0000429479596, "count": 63551, "self": 1.256538482961787, "children": { "env_step": { "total": 1014.7426177269986, "count": 63551, "self": 898.3104222679362, "children": { "SubprocessEnvManager._take_step": { "total": 115.68533203500692, "count": 63551, "self": 4.219724903947736, "children": { "TorchPolicy.evaluate": { "total": 111.46560713105919, "count": 62550, "self": 111.46560713105919 } } }, "workers": { "total": 0.7468634240553911, "count": 63551, "self": 0.0, "children": { "worker_root": { "total": 1556.4189778179402, "count": 63551, "is_parallel": true, "self": 755.2660575709788, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0022618429998146894, "count": 1, "is_parallel": true, "self": 0.0006472169993685384, "children": { "_process_rank_one_or_two_observation": { "total": 0.001614626000446151, "count": 8, "is_parallel": true, "self": 0.001614626000446151 } } }, "UnityEnvironment.step": { "total": 0.03301600699978735, "count": 1, "is_parallel": true, "self": 0.00042868199989243294, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00028445699990697904, "count": 1, "is_parallel": true, "self": 0.00028445699990697904 }, "communicator.exchange": { "total": 0.031174978999843006, "count": 1, "is_parallel": true, "self": 0.031174978999843006 }, "steps_from_proto": { "total": 0.0011278890001449327, "count": 1, "is_parallel": true, "self": 0.0002690439996513305, "children": { "_process_rank_one_or_two_observation": { "total": 0.0008588450004936021, "count": 8, "is_parallel": true, "self": 0.0008588450004936021 } } } } } } }, "UnityEnvironment.step": { "total": 801.1529202469615, "count": 63550, "is_parallel": true, "self": 21.60956478286562, "children": { "UnityEnvironment._generate_step_input": { "total": 14.269567851045394, "count": 63550, "is_parallel": true, "self": 14.269567851045394 }, "communicator.exchange": { "total": 701.3633684900055, "count": 63550, "is_parallel": true, "self": 701.3633684900055 }, "steps_from_proto": { "total": 63.9104191230449, "count": 63550, "is_parallel": true, "self": 13.668479821960773, "children": { "_process_rank_one_or_two_observation": { "total": 50.24193930108413, "count": 508400, "is_parallel": true, "self": 50.24193930108413 } } } } } } } } } } }, "trainer_advance": { "total": 539.0008867379993, "count": 63551, "self": 2.3098657240584544, "children": { "process_trajectory": { "total": 110.3931754799487, "count": 63551, "self": 110.2115140849487, "children": { "RLTrainer._checkpoint": { "total": 0.1816613949999919, "count": 2, "self": 0.1816613949999919 } } }, "_update_policy": { "total": 426.29784553399213, "count": 441, "self": 247.1402802539983, "children": { "TorchPPOOptimizer.update": { "total": 179.15756527999383, "count": 22899, "self": 179.15756527999383 } } } } } } }, "trainer_threads": { "total": 9.85000042419415e-07, "count": 1, "self": 9.85000042419415e-07 }, "TrainerController._save_models": { "total": 0.07947117899993827, "count": 1, "self": 0.001224051999997755, "children": { "RLTrainer._checkpoint": { "total": 0.07824712699994052, "count": 1, "self": 0.07824712699994052 } } } } } } }