{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3764370381832123, "min": 0.3764370381832123, "max": 1.4417481422424316, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 11353.3408203125, "min": 11353.3408203125, "max": 43736.87109375, "count": 33 }, "Pyramids.Step.mean": { "value": 989916.0, "min": 29952.0, "max": 989916.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989916.0, "min": 29952.0, "max": 989916.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5423061847686768, "min": -0.1677435040473938, "max": 0.5423061847686768, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 148.59188842773438, "min": -40.16038513183594, "max": 148.59188842773438, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.037141673266887665, "min": -0.09858638048171997, "max": 0.28736913204193115, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 10.17681884765625, "min": -25.73104476928711, "max": 68.10648345947266, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06561464295650478, "min": 0.06561464295650478, "max": 0.07342694063629521, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9186050013910668, "min": 0.4993404987108915, "max": 1.0759904589892055, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015348606916848525, "min": 0.0007480160797230538, "max": 0.015519783805861925, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21488049683587934, "min": 0.007447265527943451, "max": 0.21727697328206694, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.553776053535716e-06, "min": 7.553776053535716e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010575286474950002, "min": 0.00010575286474950002, "max": 0.0035098043300653002, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10251789285714286, "min": 0.10251789285714286, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4352505, "min": 1.3691136000000002, "max": 2.5699347000000006, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026153749642857154, "min": 0.00026153749642857154, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003661524950000001, "min": 0.003661524950000001, "max": 0.11701647653000002, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009237812831997871, "min": 0.008847196586430073, "max": 0.4051366150379181, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1293293833732605, "min": 0.12386075407266617, "max": 2.835956335067749, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 337.5813953488372, "min": 337.5813953488372, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29032.0, "min": 15984.0, "max": 32230.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.662418585357278, "min": -1.0000000521540642, "max": 1.662418585357278, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 142.9679983407259, "min": -32.000001668930054, "max": 142.9679983407259, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.662418585357278, "min": -1.0000000521540642, "max": 1.662418585357278, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 142.9679983407259, "min": -32.000001668930054, "max": 142.9679983407259, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03209847890143147, "min": 0.03209847890143147, "max": 8.360641753301024, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.7604691855231067, "min": 2.7604691855231067, "max": 133.7702680528164, "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": "1756582614", "python_version": "3.10.12 (main, Aug 15 2025, 14:32:43) [GCC 11.4.0]", "command_line_arguments": "/content/venv/bin/mlagents-learn /content/ml-agents/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": "1756584786" }, "total": 2172.5751681539996, "count": 1, "self": 0.4754665020000175, "children": { "run_training.setup": { "total": 0.017249800999707077, "count": 1, "self": 0.017249800999707077 }, "TrainerController.start_learning": { "total": 2172.082451851, "count": 1, "self": 1.3997770189916992, "children": { "TrainerController._reset_env": { "total": 2.0145106979998673, "count": 1, "self": 2.0145106979998673 }, "TrainerController.advance": { "total": 2168.571709801009, "count": 63702, "self": 1.3698076169889646, "children": { "env_step": { "total": 1508.0200891709287, "count": 63702, "self": 1359.3230032780084, "children": { "SubprocessEnvManager._take_step": { "total": 147.85998498596018, "count": 63702, "self": 4.718685250920316, "children": { "TorchPolicy.evaluate": { "total": 143.14129973503987, "count": 62555, "self": 143.14129973503987 } } }, "workers": { "total": 0.8371009069601314, "count": 63702, "self": 0.0, "children": { "worker_root": { "total": 2167.0585730859875, "count": 63702, "is_parallel": true, "self": 919.7150947380001, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001931499999955122, "count": 1, "is_parallel": true, "self": 0.0006100870000409486, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013214129999141733, "count": 8, "is_parallel": true, "self": 0.0013214129999141733 } } }, "UnityEnvironment.step": { "total": 0.05005818899962833, "count": 1, "is_parallel": true, "self": 0.0005168289990251651, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004949150002175884, "count": 1, "is_parallel": true, "self": 0.0004949150002175884 }, "communicator.exchange": { "total": 0.04733315100020263, "count": 1, "is_parallel": true, "self": 0.04733315100020263 }, "steps_from_proto": { "total": 0.001713294000182941, "count": 1, "is_parallel": true, "self": 0.00038219599991862196, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013310980002643191, "count": 8, "is_parallel": true, "self": 0.0013310980002643191 } } } } } } }, "UnityEnvironment.step": { "total": 1247.3434783479875, "count": 63701, "is_parallel": true, "self": 31.57940998194499, "children": { "UnityEnvironment._generate_step_input": { "total": 22.90420170200423, "count": 63701, "is_parallel": true, "self": 22.90420170200423 }, "communicator.exchange": { "total": 1095.1257552550355, "count": 63701, "is_parallel": true, "self": 1095.1257552550355 }, "steps_from_proto": { "total": 97.73411140900271, "count": 63701, "is_parallel": true, "self": 19.822797956030627, "children": { "_process_rank_one_or_two_observation": { "total": 77.91131345297208, "count": 509608, "is_parallel": true, "self": 77.91131345297208 } } } } } } } } } } }, "trainer_advance": { "total": 659.1818130130914, "count": 63702, "self": 2.6849666181278735, "children": { "process_trajectory": { "total": 127.56145604096355, "count": 63702, "self": 127.32716428796402, "children": { "RLTrainer._checkpoint": { "total": 0.23429175299952476, "count": 2, "self": 0.23429175299952476 } } }, "_update_policy": { "total": 528.935390354, "count": 445, "self": 294.7307436419719, "children": { "TorchPPOOptimizer.update": { "total": 234.20464671202808, "count": 22794, "self": 234.20464671202808 } } } } } } }, "trainer_threads": { "total": 9.99999429041054e-07, "count": 1, "self": 9.99999429041054e-07 }, "TrainerController._save_models": { "total": 0.0964533329997721, "count": 1, "self": 0.0014411729998755618, "children": { "RLTrainer._checkpoint": { "total": 0.09501215999989654, "count": 1, "self": 0.09501215999989654 } } } } } } }