{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.15313640236854553, "min": 0.1491367369890213, "max": 1.461522102355957, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 4608.79296875, "min": 4481.2607421875, "max": 44336.734375, "count": 100 }, "Pyramids.Step.mean": { "value": 2999939.0, "min": 29952.0, "max": 2999939.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999939.0, "min": 29952.0, "max": 2999939.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.8002849221229553, "min": -0.1223563402891159, "max": 0.8612830638885498, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 243.28662109375, "min": -28.99845314025879, "max": 258.3849182128906, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.001654613995924592, "min": -0.00840162206441164, "max": 0.3478734791278839, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 0.5030026435852051, "min": -2.15921688079834, "max": 82.44601440429688, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06586157622846908, "min": 0.06444821091506456, "max": 0.07432933354458258, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9220620671985671, "min": 0.4809304167537939, "max": 1.0895733896856352, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.017249026318452144, "min": 0.0002988890158269202, "max": 0.01863462961946858, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.24148636845833, "min": 0.0032877791740961223, "max": 0.26088481467256014, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.45688522869048e-06, "min": 1.45688522869048e-06, "max": 0.00029838354339596195, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.039639320166672e-05, "min": 2.039639320166672e-05, "max": 0.0038008565330478667, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10048559523809522, "min": 0.10048559523809522, "max": 0.19946118095238097, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4067983333333332, "min": 1.3962282666666668, "max": 2.737539033333334, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 5.8510964285714416e-05, "min": 5.8510964285714416e-05, "max": 0.009946171977142856, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.0008191535000000018, "min": 0.0008191535000000018, "max": 0.12670851812, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.00719241751357913, "min": 0.0069189821369946, "max": 0.2772340476512909, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.10069384425878525, "min": 0.09686575084924698, "max": 1.9406384229660034, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 219.84172661870502, "min": 206.19424460431654, "max": 999.0, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30558.0, "min": 15984.0, "max": 33941.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7793550641424414, "min": -1.0000000521540642, "max": 1.793805743507344, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 245.5509988516569, "min": -31.998001664876938, "max": 254.04199777543545, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7793550641424414, "min": -1.0000000521540642, "max": 1.793805743507344, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 245.5509988516569, "min": -31.998001664876938, "max": 254.04199777543545, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.016406612893278827, "min": 0.01543570772984246, "max": 5.6335464948788285, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 2.264112579272478, "min": 2.0673963893787004, "max": 90.13674391806126, "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": "1679375216", "python_version": "3.9.9 | packaged by conda-forge | (main, Dec 20 2021, 02:40:17) \n[GCC 9.4.0]", "command_line_arguments": "/home/qiang/opt/miniconda3/envs/x-hf-deeprl/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics", "mlagents_version": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.19.5", "end_time_seconds": "1679380503" }, "total": 5286.875102930935, "count": 1, "self": 0.3200054179178551, "children": { "run_training.setup": { "total": 0.016610361053608358, "count": 1, "self": 0.016610361053608358 }, "TrainerController.start_learning": { "total": 5286.538487151964, "count": 1, "self": 4.187149831326678, "children": { "TrainerController._reset_env": { "total": 3.228897077962756, "count": 1, "self": 3.228897077962756 }, "TrainerController.advance": { "total": 5279.0278340847, "count": 195082, "self": 3.8233351692324504, "children": { "env_step": { "total": 3081.3609271334717, "count": 195082, "self": 2766.362139328383, "children": { "SubprocessEnvManager._take_step": { "total": 312.45665560045745, "count": 195082, "self": 12.229900089208968, "children": { "TorchPolicy.evaluate": { "total": 300.2267555112485, "count": 187556, "self": 107.18996791588143, "children": { "TorchPolicy.sample_actions": { "total": 193.03678759536706, "count": 187556, "self": 193.03678759536706 } } } } }, "workers": { "total": 2.5421322046313435, "count": 195082, "self": 0.0, "children": { "worker_root": { "total": 5279.747725866968, "count": 195082, "is_parallel": true, "self": 2781.507334805443, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0016106260009109974, "count": 1, "is_parallel": true, "self": 0.0004166037542745471, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011940222466364503, "count": 8, "is_parallel": true, "self": 0.0011940222466364503 } } }, "UnityEnvironment.step": { "total": 0.03265785798430443, "count": 1, "is_parallel": true, "self": 0.0002808289136737585, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0006118100136518478, "count": 1, "is_parallel": true, "self": 0.0006118100136518478 }, "communicator.exchange": { "total": 0.03059137798845768, "count": 1, "is_parallel": true, "self": 0.03059137798845768 }, "steps_from_proto": { "total": 0.001173841068521142, "count": 1, "is_parallel": true, "self": 0.00022726005408912897, "children": { "_process_rank_one_or_two_observation": { "total": 0.000946581014432013, "count": 8, "is_parallel": true, "self": 0.000946581014432013 } } } } } } }, "UnityEnvironment.step": { "total": 2498.240391061525, "count": 195081, "is_parallel": true, "self": 57.95700426143594, "children": { "UnityEnvironment._generate_step_input": { "total": 46.52879376744386, "count": 195081, "is_parallel": true, "self": 46.52879376744386 }, "communicator.exchange": { "total": 2118.264028996695, "count": 195081, "is_parallel": true, "self": 2118.264028996695 }, "steps_from_proto": { "total": 275.49056403595023, "count": 195081, "is_parallel": true, "self": 48.38291724619921, "children": { "_process_rank_one_or_two_observation": { "total": 227.10764678975102, "count": 1560648, "is_parallel": true, "self": 227.10764678975102 } } } } } } } } } } }, "trainer_advance": { "total": 2193.8435717819957, "count": 195082, "self": 7.84908934996929, "children": { "process_trajectory": { "total": 433.3110535793239, "count": 195082, "self": 432.74776552128606, "children": { "RLTrainer._checkpoint": { "total": 0.5632880580378696, "count": 6, "self": 0.5632880580378696 } } }, "_update_policy": { "total": 1752.6834288527025, "count": 1393, "self": 652.2041771702934, "children": { "TorchPPOOptimizer.update": { "total": 1100.479251682409, "count": 68358, "self": 1100.479251682409 } } } } } } }, "trainer_threads": { "total": 8.050119504332542e-07, "count": 1, "self": 8.050119504332542e-07 }, "TrainerController._save_models": { "total": 0.09460535296238959, "count": 1, "self": 0.001206306042149663, "children": { "RLTrainer._checkpoint": { "total": 0.09339904692023993, "count": 1, "self": 0.09339904692023993 } } } } } } }