{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.481205016374588, "min": 0.48030582070350647, "max": 1.4284112453460693, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 14336.0595703125, "min": 14336.0595703125, "max": 43332.28515625, "count": 33 }, "Pyramids.Step.mean": { "value": 989927.0, "min": 29952.0, "max": 989927.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989927.0, "min": 29952.0, "max": 989927.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.43018174171447754, "min": -0.1143270954489708, "max": 0.4550936818122864, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 116.1490707397461, "min": -27.667156219482422, "max": 122.87529754638672, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.6551812887191772, "min": -0.6551812887191772, "max": 0.5367847681045532, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -176.89894104003906, "min": -176.89894104003906, "max": 127.2179946899414, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06948731025369155, "min": 0.06259305740583358, "max": 0.07258572059522739, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9728223435516816, "min": 0.47814315712031236, "max": 1.0347706072737792, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.06508450182025967, "min": 0.00031050211099229217, "max": 0.06508450182025967, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.9111830254836354, "min": 0.003415523220915214, "max": 0.9111830254836354, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.462854655271425e-06, "min": 7.462854655271425e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010447996517379995, "min": 0.00010447996517379995, "max": 0.0033825242724919995, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10248758571428575, "min": 0.10248758571428575, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4348262000000005, "min": 1.3691136000000002, "max": 2.5275079999999996, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025850981285714274, "min": 0.00025850981285714274, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003619137379999998, "min": 0.003619137379999998, "max": 0.11277804920000002, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.012500987388193607, "min": 0.011927835643291473, "max": 0.8109455704689026, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.17501382529735565, "min": 0.16698969900608063, "max": 5.676619052886963, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 414.07142857142856, "min": 409.7638888888889, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28985.0, "min": 15984.0, "max": 32035.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.500197122352464, "min": -1.0000000521540642, "max": 1.500197122352464, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 105.01379856467247, "min": -32.000001668930054, "max": 105.01379856467247, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.500197122352464, "min": -1.0000000521540642, "max": 1.500197122352464, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 105.01379856467247, "min": -32.000001668930054, "max": 105.01379856467247, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.05434330895908975, "min": 0.05434330895908975, "max": 18.895740719512105, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.8040316271362826, "min": 3.786718374234624, "max": 302.3318515121937, "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": "1730745961", "python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.5.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1730748096" }, "total": 2135.5665269759997, "count": 1, "self": 0.4968105409998316, "children": { "run_training.setup": { "total": 0.053362533999916195, "count": 1, "self": 0.053362533999916195 }, "TrainerController.start_learning": { "total": 2135.016353901, "count": 1, "self": 1.327881034053462, "children": { "TrainerController._reset_env": { "total": 2.201502222000272, "count": 1, "self": 2.201502222000272 }, "TrainerController.advance": { "total": 2131.405917236947, "count": 63544, "self": 1.3346329767332463, "children": { "env_step": { "total": 1456.3662775501293, "count": 63544, "self": 1314.7503753071392, "children": { "SubprocessEnvManager._take_step": { "total": 140.82990737398086, "count": 63544, "self": 4.389269913881435, "children": { "TorchPolicy.evaluate": { "total": 136.44063746009942, "count": 62554, "self": 136.44063746009942 } } }, "workers": { "total": 0.7859948690093006, "count": 63544, "self": 0.0, "children": { "worker_root": { "total": 2130.316078510896, "count": 63544, "is_parallel": true, "self": 926.8083048088197, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001967577999948844, "count": 1, "is_parallel": true, "self": 0.0006009279991303629, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013666500008184812, "count": 8, "is_parallel": true, "self": 0.0013666500008184812 } } }, "UnityEnvironment.step": { "total": 0.05002074799995171, "count": 1, "is_parallel": true, "self": 0.0007483800000045449, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004531769995992363, "count": 1, "is_parallel": true, "self": 0.0004531769995992363 }, "communicator.exchange": { "total": 0.04720093600008113, "count": 1, "is_parallel": true, "self": 0.04720093600008113 }, "steps_from_proto": { "total": 0.0016182550002667995, "count": 1, "is_parallel": true, "self": 0.00033259600058954675, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012856589996772527, "count": 8, "is_parallel": true, "self": 0.0012856589996772527 } } } } } } }, "UnityEnvironment.step": { "total": 1203.5077737020765, "count": 63543, "is_parallel": true, "self": 32.21553660620884, "children": { "UnityEnvironment._generate_step_input": { "total": 22.66555169093499, "count": 63543, "is_parallel": true, "self": 22.66555169093499 }, "communicator.exchange": { "total": 1055.52805240304, "count": 63543, "is_parallel": true, "self": 1055.52805240304 }, "steps_from_proto": { "total": 93.09863300189272, "count": 63543, "is_parallel": true, "self": 18.52459491071295, "children": { "_process_rank_one_or_two_observation": { "total": 74.57403809117977, "count": 508344, "is_parallel": true, "self": 74.57403809117977 } } } } } } } } } } }, "trainer_advance": { "total": 673.7050067100845, "count": 63544, "self": 2.466302348078898, "children": { "process_trajectory": { "total": 128.4772499810124, "count": 63544, "self": 128.28660351701274, "children": { "RLTrainer._checkpoint": { "total": 0.19064646399965568, "count": 2, "self": 0.19064646399965568 } } }, "_update_policy": { "total": 542.7614543809932, "count": 441, "self": 306.70749331798334, "children": { "TorchPPOOptimizer.update": { "total": 236.05396106300987, "count": 22842, "self": 236.05396106300987 } } } } } } }, "trainer_threads": { "total": 9.489995136391371e-07, "count": 1, "self": 9.489995136391371e-07 }, "TrainerController._save_models": { "total": 0.08105245899969304, "count": 1, "self": 0.002006644999710261, "children": { "RLTrainer._checkpoint": { "total": 0.07904581399998278, "count": 1, "self": 0.07904581399998278 } } } } } } }