{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.6952756643295288, "min": 0.6952756643295288, "max": 0.7228708863258362, "count": 2 }, "Pyramids.Policy.Entropy.sum": { "value": 20602.408203125, "min": 15810.6318359375, "max": 20602.408203125, "count": 2 }, "Pyramids.Step.mean": { "value": 599925.0, "min": 569959.0, "max": 599925.0, "count": 2 }, "Pyramids.Step.sum": { "value": 599925.0, "min": 569959.0, "max": 599925.0, "count": 2 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.3051663041114807, "min": 0.3051663041114807, "max": 0.31641384959220886, "count": 2 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 78.42774200439453, "min": 57.587318420410156, "max": 78.42774200439453, "count": 2 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.03122531622648239, "min": 0.029503462836146355, "max": 0.03122531622648239, "count": 2 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 8.024906158447266, "min": 5.369630336761475, "max": 8.024906158447266, "count": 2 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 553.0816326530612, "min": 428.35, "max": 553.0816326530612, "count": 2 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 27101.0, "min": 17134.0, "max": 27101.0, "count": 2 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.2019387472953116, "min": 1.2019387472953116, "max": 1.421574972756207, "count": 2 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 58.894998617470264, "min": 56.86299891024828, "max": 58.894998617470264, "count": 2 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.2019387472953116, "min": 1.2019387472953116, "max": 1.421574972756207, "count": 2 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 58.894998617470264, "min": 56.86299891024828, "max": 58.894998617470264, "count": 2 }, "Pyramids.Policy.RndReward.mean": { "value": 0.11890821227487842, "min": 0.09293368358776206, "max": 0.11890821227487842, "count": 2 }, "Pyramids.Policy.RndReward.sum": { "value": 5.8265024014690425, "min": 3.7173473435104825, "max": 5.8265024014690425, "count": 2 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0656754122276191, "min": 0.0656754122276191, "max": 0.06623300981677689, "count": 2 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9194557711866675, "min": 0.5960970883509921, "max": 0.9194557711866675, "count": 2 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.011471936822199904, "min": 0.011471936822199904, "max": 0.011659463921306372, "count": 2 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.16060711551079865, "min": 0.10493517529175735, "max": 0.16060711551079865, "count": 2 }, "Pyramids.Policy.LearningRate.mean": { "value": 0.00012472141556907142, "min": 0.00012472141556907142, "max": 0.0001320175559941667, "count": 2 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.001746099817967, "min": 0.0011881580039475002, "max": 0.001746099817967, "count": 2 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.14157378571428572, "min": 0.14157378571428572, "max": 0.14400583333333336, "count": 2 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.982033, "min": 1.2960525000000003, "max": 1.982033, "count": 2 }, "Pyramids.Policy.Beta.mean": { "value": 0.0041632211928571425, "min": 0.0041632211928571425, "max": 0.00440618275, "count": 2 }, "Pyramids.Policy.Beta.sum": { "value": 0.0582850967, "min": 0.03965564475, "max": 0.0582850967, "count": 2 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.020621448755264282, "min": 0.020621448755264282, "max": 0.021258942782878876, "count": 2 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.28870028257369995, "min": 0.19133047759532928, "max": 0.28870028257369995, "count": 2 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 2 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 2 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1714275379", "python_version": "3.10.12 | packaged by conda-forge | (main, Jun 23 2023, 22:40:32) [GCC 12.3.0]", "command_line_arguments": "/home/saini5/miniforge3/envs/hf_rl_mlagents_env/bin/mlagents-learn ml-agents/config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --resume", "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": "1714275494" }, "total": 115.7308161309993, "count": 1, "self": 0.28315517800001544, "children": { "run_training.setup": { "total": 0.011984718999883626, "count": 1, "self": 0.011984718999883626 }, "TrainerController.start_learning": { "total": 115.4356762339994, "count": 1, "self": 0.07451290999779303, "children": { "TrainerController._reset_env": { "total": 3.4376514420000603, "count": 1, "self": 3.4376514420000603 }, "TrainerController.advance": { "total": 111.83582807700259, "count": 3465, "self": 0.08447649202389584, "children": { "env_step": { "total": 89.24504656496174, "count": 3465, "self": 83.32598049001899, "children": { "SubprocessEnvManager._take_step": { "total": 5.86615790896758, "count": 3465, "self": 0.2324731719400006, "children": { "TorchPolicy.evaluate": { "total": 5.633684737027579, "count": 3393, "self": 5.633684737027579 } } }, "workers": { "total": 0.05290816597516823, "count": 3464, "self": 0.0, "children": { "worker_root": { "total": 115.17828353205186, "count": 3464, "is_parallel": true, "self": 37.38909135808899, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0013480579982569907, "count": 1, "is_parallel": true, "self": 0.00042823799958569, "children": { "_process_rank_one_or_two_observation": { "total": 0.0009198199986713007, "count": 8, "is_parallel": true, "self": 0.0009198199986713007 } } }, "UnityEnvironment.step": { "total": 0.03467490299954079, "count": 1, "is_parallel": true, "self": 0.00019506200078467373, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003417369989620056, "count": 1, "is_parallel": true, "self": 0.0003417369989620056 }, "communicator.exchange": { "total": 0.033656734000032884, "count": 1, "is_parallel": true, "self": 0.033656734000032884 }, "steps_from_proto": { "total": 0.0004813699997612275, "count": 1, "is_parallel": true, "self": 0.00011746399832190946, "children": { "_process_rank_one_or_two_observation": { "total": 0.00036390600143931806, "count": 8, "is_parallel": true, "self": 0.00036390600143931806 } } } } } } }, "UnityEnvironment.step": { "total": 77.78919217396287, "count": 3463, "is_parallel": true, "self": 1.0151009270630311, "children": { "UnityEnvironment._generate_step_input": { "total": 0.8757327639050345, "count": 3463, "is_parallel": true, "self": 0.8757327639050345 }, "communicator.exchange": { "total": 73.00172853798904, "count": 3463, "is_parallel": true, "self": 73.00172853798904 }, "steps_from_proto": { "total": 2.8966299450057704, "count": 3463, "is_parallel": true, "self": 0.6936075289377186, "children": { "_process_rank_one_or_two_observation": { "total": 2.203022416068052, "count": 27704, "is_parallel": true, "self": 2.203022416068052 } } } } } } } } } } }, "trainer_advance": { "total": 22.506305020016953, "count": 3464, "self": 0.13575411398960568, "children": { "process_trajectory": { "total": 4.324522689030346, "count": 3464, "self": 4.324522689030346 }, "_update_policy": { "total": 18.046028216997, "count": 25, "self": 8.686620139034858, "children": { "TorchPPOOptimizer.update": { "total": 9.359408077962144, "count": 1203, "self": 9.359408077962144 } } } } } } }, "trainer_threads": { "total": 1.4519991964334622e-06, "count": 1, "self": 1.4519991964334622e-06 }, "TrainerController._save_models": { "total": 0.08768235299976368, "count": 1, "self": 0.0018772519997583004, "children": { "RLTrainer._checkpoint": { "total": 0.08580510100000538, "count": 1, "self": 0.08580510100000538 } } } } } } }