{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.2483118325471878, "min": 0.2483118325471878, "max": 1.3020858764648438, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 7429.490234375, "min": 7429.490234375, "max": 39500.078125, "count": 33 }, "Pyramids.Step.mean": { "value": 989981.0, "min": 29920.0, "max": 989981.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989981.0, "min": 29920.0, "max": 989981.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.39218398928642273, "min": -0.0870528593659401, "max": 0.4853465259075165, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 103.92875671386719, "min": -21.066791534423828, "max": 132.49960327148438, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.006078196689486504, "min": -0.00937902182340622, "max": 0.37689024209976196, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 1.6107220649719238, "min": -2.5041987895965576, "max": 89.69987487792969, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07033957654216681, "min": 0.06453300546023197, "max": 0.07142242988038688, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9847540715903355, "min": 0.6421208856188566, "max": 1.0606377206887712, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014294611059345439, "min": 0.0008860305375570322, "max": 0.0153022868873363, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.20012455483083613, "min": 0.01240442752579845, "max": 0.2142320164227082, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.617333175207144e-06, "min": 7.617333175207144e-06, "max": 0.00029479770173409994, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010664266445290002, "min": 0.00010664266445290002, "max": 0.0037608760463747, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10253907857142859, "min": 0.10253907857142859, "max": 0.1982659, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4355471000000002, "min": 1.4355471000000002, "max": 2.6536253000000003, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026365394928571436, "min": 0.00026365394928571436, "max": 0.009826763410000001, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003691155290000001, "min": 0.003691155290000001, "max": 0.12537716747000002, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010552129708230495, "min": 0.010552129708230495, "max": 0.41967830061912537, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1477298140525818, "min": 0.1477298140525818, "max": 3.777104616165161, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 431.2647058823529, "min": 390.7088607594937, "max": 995.1379310344828, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29326.0, "min": 18125.0, "max": 32311.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.215697034207337, "min": -0.9282063022255898, "max": 1.4844424822367728, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 82.66739832609892, "min": -29.702601671218872, "max": 118.75539857894182, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.215697034207337, "min": -0.9282063022255898, "max": 1.4844424822367728, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 82.66739832609892, "min": -29.702601671218872, "max": 118.75539857894182, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.048261534201789316, "min": 0.043455076151076355, "max": 7.120167306379268, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.2817843257216737, "min": 3.203845447918866, "max": 135.2831788212061, "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": "1757411623", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/home/lx/miniconda3/envs/py310/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1757414268" }, "total": 2644.6988556999713, "count": 1, "self": 0.42388459760695696, "children": { "run_training.setup": { "total": 0.020595133304595947, "count": 1, "self": 0.020595133304595947 }, "TrainerController.start_learning": { "total": 2644.2543759690598, "count": 1, "self": 0.9682086873799562, "children": { "TrainerController._reset_env": { "total": 2.6868187207728624, "count": 1, "self": 2.6868187207728624 }, "TrainerController.advance": { "total": 2640.5181416012347, "count": 63847, "self": 0.9881900297477841, "children": { "env_step": { "total": 1789.8880913071334, "count": 63847, "self": 1673.9289362896234, "children": { "SubprocessEnvManager._take_step": { "total": 115.36157827358693, "count": 63847, "self": 3.54991355817765, "children": { "TorchPolicy.evaluate": { "total": 111.81166471540928, "count": 62572, "self": 111.81166471540928 } } }, "workers": { "total": 0.5975767439231277, "count": 63847, "self": 0.0, "children": { "worker_root": { "total": 2639.8886667350307, "count": 63847, "is_parallel": true, "self": 1080.6705891462043, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004789501428604126, "count": 1, "is_parallel": true, "self": 0.0013112546876072884, "children": { "_process_rank_one_or_two_observation": { "total": 0.0034782467409968376, "count": 8, "is_parallel": true, "self": 0.0034782467409968376 } } }, "UnityEnvironment.step": { "total": 0.061963727697730064, "count": 1, "is_parallel": true, "self": 0.0009860675781965256, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0008709868416190147, "count": 1, "is_parallel": true, "self": 0.0008709868416190147 }, "communicator.exchange": { "total": 0.057119748555123806, "count": 1, "is_parallel": true, "self": 0.057119748555123806 }, "steps_from_proto": { "total": 0.002986924722790718, "count": 1, "is_parallel": true, "self": 0.0006400048732757568, "children": { "_process_rank_one_or_two_observation": { "total": 0.0023469198495149612, "count": 8, "is_parallel": true, "self": 0.0023469198495149612 } } } } } } }, "UnityEnvironment.step": { "total": 1559.2180775888264, "count": 63846, "is_parallel": true, "self": 60.74290841817856, "children": { "UnityEnvironment._generate_step_input": { "total": 42.834331303834915, "count": 63846, "is_parallel": true, "self": 42.834331303834915 }, "communicator.exchange": { "total": 1280.8276186781004, "count": 63846, "is_parallel": true, "self": 1280.8276186781004 }, "steps_from_proto": { "total": 174.81321918871254, "count": 63846, "is_parallel": true, "self": 36.027208937332034, "children": { "_process_rank_one_or_two_observation": { "total": 138.7860102513805, "count": 510768, "is_parallel": true, "self": 138.7860102513805 } } } } } } } } } } }, "trainer_advance": { "total": 849.6418602643535, "count": 63847, "self": 1.8793002543970942, "children": { "process_trajectory": { "total": 102.56322802696377, "count": 63847, "self": 102.38093100022525, "children": { "RLTrainer._checkpoint": { "total": 0.18229702673852444, "count": 2, "self": 0.18229702673852444 } } }, "_update_policy": { "total": 745.1993319829926, "count": 462, "self": 336.2539898818359, "children": { "TorchPPOOptimizer.update": { "total": 408.9453421011567, "count": 22779, "self": 408.9453421011567 } } } } } } }, "trainer_threads": { "total": 1.043081283569336e-06, "count": 1, "self": 1.043081283569336e-06 }, "TrainerController._save_models": { "total": 0.08120591659098864, "count": 1, "self": 0.0009952392429113388, "children": { "RLTrainer._checkpoint": { "total": 0.0802106773480773, "count": 1, "self": 0.0802106773480773 } } } } } } }