{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4368692636489868, "min": 0.4308827519416809, "max": 1.6023768186569214, "count": 50 }, "Pyramids.Policy.Entropy.sum": { "value": 8751.365234375, "min": 8659.01953125, "max": 32201.365234375, "count": 50 }, "Pyramids.Step.mean": { "value": 999892.0, "min": 19968.0, "max": 999892.0, "count": 50 }, "Pyramids.Step.sum": { "value": 999892.0, "min": 19968.0, "max": 999892.0, "count": 50 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": -0.07685001194477081, "min": -0.1043524369597435, "max": -0.0594039112329483, "count": 50 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": -12.296002388000488, "min": -16.851215362548828, "max": -9.564029693603516, "count": 50 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.0173623226583004, "min": 0.01718338020145893, "max": 0.3498693108558655, "count": 50 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 2.7779715061187744, "min": 2.7560315132141113, "max": 55.62921905517578, "count": 50 }, "Pyramids.Policy.CuriosityValueEstimate.mean": { "value": 0.07259224355220795, "min": 0.032525256276130676, "max": 0.2536250948905945, "count": 50 }, "Pyramids.Policy.CuriosityValueEstimate.sum": { "value": 11.61475944519043, "min": 5.171515464782715, "max": 40.580013275146484, "count": 50 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06893045877513941, "min": 0.05804945588942594, "max": 0.07661458291947895, "count": 50 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.13786091755027882, "min": 0.06736144984897692, "max": 0.15150092454213235, "count": 50 }, "Pyramids.Losses.ValueLoss.mean": { "value": 6.862680124299913e-05, "min": 1.0468886299008772e-05, "max": 0.015604345289628126, "count": 50 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.00013725360248599826, "min": 1.9393958666569233e-05, "max": 0.015604345289628126, "count": 50 }, "Pyramids.Policy.LearningRate.mean": { "value": 3.240098919999993e-06, "min": 3.240098919999993e-06, "max": 0.00029631360122879996, "count": 50 }, "Pyramids.Policy.LearningRate.sum": { "value": 6.480197839999986e-06, "min": 6.480197839999986e-06, "max": 0.0005819136060287999, "count": 50 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10162000000000002, "min": 0.10162000000000002, "max": 0.24815680000000004, "count": 50 }, "Pyramids.Policy.Epsilon.sum": { "value": 0.20324000000000003, "min": 0.12249219999999995, "max": 0.4909568000000001, "count": 50 }, "Pyramids.Policy.Beta.mean": { "value": 2.069199999999997e-05, "min": 2.069199999999997e-05, "max": 0.00098783488, "count": 50 }, "Pyramids.Policy.Beta.sum": { "value": 4.138399999999994e-05, "min": 4.138399999999994e-05, "max": 0.0019403148800000002, "count": 50 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01641818881034851, "min": 0.014551613479852676, "max": 0.8168574571609497, "count": 50 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.03283637762069702, "min": 0.017075607553124428, "max": 0.8168574571609497, "count": 50 }, "Pyramids.Losses.CuriosityForwardLoss.mean": { "value": 0.06454861147794873, "min": 0.06454861147794873, "max": 0.5022600194853213, "count": 50 }, "Pyramids.Losses.CuriosityForwardLoss.sum": { "value": 0.12909722295589746, "min": 0.07133469521068037, "max": 0.5236991447788002, "count": 50 }, "Pyramids.Losses.CuriosityInverseLoss.mean": { "value": 0.0685774822505967, "min": 0.06479755593463779, "max": 0.9341130413942866, "count": 50 }, "Pyramids.Losses.CuriosityInverseLoss.sum": { "value": 0.1371549645011934, "min": 0.07756975268324216, "max": 1.1713232168373668, "count": 50 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 999.0, "min": 889.15, "max": 999.0, "count": 50 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 19980.0, "min": 15039.0, "max": 31968.0, "count": 50 }, "Pyramids.Environment.CumulativeReward.mean": { "value": -0.9997000526636839, "min": -1.0000000521540642, "max": -0.47678952193573904, "count": 50 }, "Pyramids.Environment.CumulativeReward.sum": { "value": -19.994001053273678, "min": -31.99920167028904, "max": -9.059000916779041, "count": 50 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": -0.9997000526636839, "min": -1.0000000521540642, "max": -0.47678952193573904, "count": 50 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": -19.994001053273678, "min": -31.99920167028904, "max": -9.059000916779041, "count": 50 }, "Pyramids.Policy.RndReward.mean": { "value": 0.16850452576763927, "min": 0.1461322949693093, "max": 17.824592078104615, "count": 50 }, "Pyramids.Policy.RndReward.sum": { "value": 3.3700905153527856, "min": 2.6850122353062034, "max": 285.19347324967384, "count": 50 }, "Pyramids.Policy.CuriosityReward.mean": { "value": 0.6733389327302575, "min": 0.6435650361134954, "max": 3.64256305526942, "count": 50 }, "Pyramids.Policy.CuriosityReward.sum": { "value": 13.46677865460515, "min": 11.854416705667973, "max": 107.61907610297203, "count": 50 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 50 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 50 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1766092466", "python_version": "3.10.12 (main, Nov 4 2025, 08:48:33) [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": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1766096460" }, "total": 3993.6023549690003, "count": 1, "self": 0.811768376001055, "children": { "run_training.setup": { "total": 0.04085086099985347, "count": 1, "self": 0.04085086099985347 }, "TrainerController.start_learning": { "total": 3992.7497357319994, "count": 1, "self": 2.3739707189783985, "children": { "TrainerController._reset_env": { "total": 3.183051900999999, "count": 1, "self": 3.183051900999999 }, "TrainerController.advance": { "total": 3986.9343676280205, "count": 62985, "self": 2.4794799581022744, "children": { "env_step": { "total": 2064.8888257369913, "count": 62985, "self": 1874.1203932320477, "children": { "SubprocessEnvManager._take_step": { "total": 189.3285083650244, "count": 62985, "self": 7.631458312866471, "children": { "TorchPolicy.evaluate": { "total": 181.69705005215792, "count": 62557, "self": 181.69705005215792 } } }, "workers": { "total": 1.439924139919185, "count": 62985, "self": 0.0, "children": { "worker_root": { "total": 3984.631569267093, "count": 62985, "is_parallel": true, "self": 2292.9114663560745, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0035667199999807053, "count": 1, "is_parallel": true, "self": 0.0013955640006315662, "children": { "_process_rank_one_or_two_observation": { "total": 0.002171155999349139, "count": 8, "is_parallel": true, "self": 0.002171155999349139 } } }, "UnityEnvironment.step": { "total": 0.07281096699989575, "count": 1, "is_parallel": true, "self": 0.0007347069999923406, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005616630000986333, "count": 1, "is_parallel": true, "self": 0.0005616630000986333 }, "communicator.exchange": { "total": 0.06920479400014301, "count": 1, "is_parallel": true, "self": 0.06920479400014301 }, "steps_from_proto": { "total": 0.0023098029996617697, "count": 1, "is_parallel": true, "self": 0.00047800899938010843, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018317940002816613, "count": 8, "is_parallel": true, "self": 0.0018317940002816613 } } } } } } }, "UnityEnvironment.step": { "total": 1691.7201029110183, "count": 62984, "is_parallel": true, "self": 46.09102295205912, "children": { "UnityEnvironment._generate_step_input": { "total": 31.606381755063012, "count": 62984, "is_parallel": true, "self": 31.606381755063012 }, "communicator.exchange": { "total": 1467.7338906199088, "count": 62984, "is_parallel": true, "self": 1467.7338906199088 }, "steps_from_proto": { "total": 146.28880758398736, "count": 62984, "is_parallel": true, "self": 29.585931012516085, "children": { "_process_rank_one_or_two_observation": { "total": 116.70287657147128, "count": 503872, "is_parallel": true, "self": 116.70287657147128 } } } } } } } } } } }, "trainer_advance": { "total": 1919.566061932927, "count": 62985, "self": 4.029967697950269, "children": { "process_trajectory": { "total": 210.87578020897672, "count": 62985, "self": 210.34872139497747, "children": { "RLTrainer._checkpoint": { "total": 0.5270588139992469, "count": 2, "self": 0.5270588139992469 } } }, "_update_policy": { "total": 1704.660314026, "count": 94, "self": 794.2426236510391, "children": { "TorchPPOOptimizer.update": { "total": 910.4176903749608, "count": 23187, "self": 910.4176903749608 } } } } } } }, "trainer_threads": { "total": 1.4810002539888956e-06, "count": 1, "self": 1.4810002539888956e-06 }, "TrainerController._save_models": { "total": 0.2583440030002748, "count": 1, "self": 0.011337405000631406, "children": { "RLTrainer._checkpoint": { "total": 0.24700659799964342, "count": 1, "self": 0.24700659799964342 } } } } } } }