{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.2706488370895386, "min": 0.2706488370895386, "max": 1.4140993356704712, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 8041.51806640625, "min": 8041.51806640625, "max": 42898.1171875, "count": 33 }, "Pyramids.Step.mean": { "value": 989887.0, "min": 29952.0, "max": 989887.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989887.0, "min": 29952.0, "max": 989887.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5846561193466187, "min": -0.1054370105266571, "max": 0.6861109733581543, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 162.53440856933594, "min": -25.304882049560547, "max": 196.91384887695312, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.021212447434663773, "min": 0.012415816076099873, "max": 0.3839993178844452, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 5.897060394287109, "min": 3.5385074615478516, "max": 92.15983581542969, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06995712166965296, "min": 0.06573787074607336, "max": 0.07270341608470342, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9793997033751414, "min": 0.4970501582650066, "max": 1.0813259686692618, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01683889604913017, "min": 0.0007909090111249164, "max": 0.017913919018967276, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2357445446878224, "min": 0.005536363077874415, "max": 0.25079486626554187, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.339147553650003e-06, "min": 7.339147553650003e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010274806575110004, "min": 0.00010274806575110004, "max": 0.0035070020309993996, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10244635000000002, "min": 0.10244635000000002, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4342489000000003, "min": 1.3691136000000002, "max": 2.5690006000000007, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002543903650000001, "min": 0.0002543903650000001, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003561465110000002, "min": 0.003561465110000002, "max": 0.11692315994, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.015463515184819698, "min": 0.015463515184819698, "max": 0.5813530087471008, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.21648921072483063, "min": 0.21648921072483063, "max": 4.0694708824157715, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 310.0416666666667, "min": 274.55, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29764.0, "min": 15984.0, "max": 33347.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6274374838297565, "min": -1.0000000521540642, "max": 1.7054439856112003, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 156.23399844765663, "min": -32.000001668930054, "max": 174.9041977673769, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6274374838297565, "min": -1.0000000521540642, "max": 1.7054439856112003, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 156.23399844765663, "min": -32.000001668930054, "max": 174.9041977673769, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.049932735419436845, "min": 0.049932735419436845, "max": 10.908740980550647, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.793542600265937, "min": 4.793542600265937, "max": 174.53985568881035, "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": "1728973721", "python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn /content/ml-agents/config/ppo/PyramidsRND.yaml --env=/content/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": "2.4.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1728976081" }, "total": 2360.5425193270003, "count": 1, "self": 0.4818942980000429, "children": { "run_training.setup": { "total": 0.05113854699993681, "count": 1, "self": 0.05113854699993681 }, "TrainerController.start_learning": { "total": 2360.0094864820003, "count": 1, "self": 1.3470938450141148, "children": { "TrainerController._reset_env": { "total": 1.5486128089999056, "count": 1, "self": 1.5486128089999056 }, "TrainerController.advance": { "total": 2357.0476535799858, "count": 64174, "self": 1.3557725849050257, "children": { "env_step": { "total": 1561.5170555571244, "count": 64174, "self": 1458.8952511401897, "children": { "SubprocessEnvManager._take_step": { "total": 101.84373387397136, "count": 64174, "self": 4.381005242929859, "children": { "TorchPolicy.evaluate": { "total": 97.4627286310415, "count": 62568, "self": 97.4627286310415 } } }, "workers": { "total": 0.7780705429634054, "count": 64174, "self": 0.0, "children": { "worker_root": { "total": 2354.9393704389736, "count": 64174, "is_parallel": true, "self": 1015.6239321770354, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0021025190001182636, "count": 1, "is_parallel": true, "self": 0.0006312069999694359, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014713120001488278, "count": 8, "is_parallel": true, "self": 0.0014713120001488278 } } }, "UnityEnvironment.step": { "total": 0.05089644500003487, "count": 1, "is_parallel": true, "self": 0.006391790999941804, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004558680000172899, "count": 1, "is_parallel": true, "self": 0.0004558680000172899 }, "communicator.exchange": { "total": 0.04225997499997902, "count": 1, "is_parallel": true, "self": 0.04225997499997902 }, "steps_from_proto": { "total": 0.0017888110000967572, "count": 1, "is_parallel": true, "self": 0.000342459000648887, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014463519994478702, "count": 8, "is_parallel": true, "self": 0.0014463519994478702 } } } } } } }, "UnityEnvironment.step": { "total": 1339.3154382619382, "count": 64173, "is_parallel": true, "self": 32.93599501980407, "children": { "UnityEnvironment._generate_step_input": { "total": 22.551570996071177, "count": 64173, "is_parallel": true, "self": 22.551570996071177 }, "communicator.exchange": { "total": 1188.9584581990434, "count": 64173, "is_parallel": true, "self": 1188.9584581990434 }, "steps_from_proto": { "total": 94.86941404701952, "count": 64173, "is_parallel": true, "self": 18.838409758879834, "children": { "_process_rank_one_or_two_observation": { "total": 76.03100428813968, "count": 513384, "is_parallel": true, "self": 76.03100428813968 } } } } } } } } } } }, "trainer_advance": { "total": 794.1748254379563, "count": 64174, "self": 2.5780611429786404, "children": { "process_trajectory": { "total": 124.92222548597306, "count": 64174, "self": 124.78154933297333, "children": { "RLTrainer._checkpoint": { "total": 0.14067615299973113, "count": 2, "self": 0.14067615299973113 } } }, "_update_policy": { "total": 666.6745388090046, "count": 449, "self": 283.3566745999701, "children": { "TorchPPOOptimizer.update": { "total": 383.3178642090345, "count": 22830, "self": 383.3178642090345 } } } } } } }, "trainer_threads": { "total": 1.0030003068095539e-06, "count": 1, "self": 1.0030003068095539e-06 }, "TrainerController._save_models": { "total": 0.06612524499996653, "count": 1, "self": 0.0019026139998459257, "children": { "RLTrainer._checkpoint": { "total": 0.0642226310001206, "count": 1, "self": 0.0642226310001206 } } } } } } }