{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.49290376901626587, "min": 0.46733948588371277, "max": 1.4683992862701416, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 14668.81640625, "min": 14117.3916015625, "max": 44545.359375, "count": 33 }, "Pyramids.Step.mean": { "value": 989961.0, "min": 29952.0, "max": 989961.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989961.0, "min": 29952.0, "max": 989961.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.20911282300949097, "min": -0.10296332091093063, "max": 0.23147255182266235, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 53.53288269042969, "min": -24.82671356201172, "max": 59.25697326660156, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.016539640724658966, "min": -0.005268581677228212, "max": 0.1927923709154129, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 4.234148025512695, "min": -1.343488335609436, "max": 45.69179153442383, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06700665444142677, "min": 0.0634705847700884, "max": 0.07259749643614595, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9380931621799748, "min": 0.4809198358075107, "max": 1.0359234969412985, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.011026443342181934, "min": 0.00014893949040922037, "max": 0.011647734584715049, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.15437020679054708, "min": 0.0019362133753198648, "max": 0.1676130302557973, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.236954730571428e-06, "min": 7.236954730571428e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.000101317366228, "min": 0.000101317366228, "max": 0.0031379879540041, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10241228571428573, "min": 0.10241228571428573, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4337720000000003, "min": 1.3691136000000002, "max": 2.3586203, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002509873428571429, "min": 0.0002509873428571429, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035138228000000005, "min": 0.0035138228000000005, "max": 0.10462499041000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010375398211181164, "min": 0.010375398211181164, "max": 0.32566165924072266, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.14525558054447174, "min": 0.14525558054447174, "max": 2.2796316146850586, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 591.06, "min": 581.7142857142857, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29553.0, "min": 15984.0, "max": 32419.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.888783965408802, "min": -1.0000000521540642, "max": 1.0508326273791644, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 44.4391982704401, "min": -32.000001668930054, "max": 51.490798741579056, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.888783965408802, "min": -1.0000000521540642, "max": 1.0508326273791644, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 44.4391982704401, "min": -32.000001668930054, "max": 51.490798741579056, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.0627848851075396, "min": 0.0627848851075396, "max": 6.402291734702885, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.1392442553769797, "min": 3.1392442553769797, "max": 102.43666775524616, "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": "1774201203", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "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": "1774204416" }, "total": 3212.600859452, "count": 1, "self": 1.1566573569998582, "children": { "run_training.setup": { "total": 0.03329422199931287, "count": 1, "self": 0.03329422199931287 }, "TrainerController.start_learning": { "total": 3211.4109078730007, "count": 1, "self": 2.1658443589840317, "children": { "TrainerController._reset_env": { "total": 3.857052850999935, "count": 1, "self": 3.857052850999935 }, "TrainerController.advance": { "total": 3205.2867976700145, "count": 63341, "self": 2.362063186859814, "children": { "env_step": { "total": 2079.856296831038, "count": 63341, "self": 1911.439863480975, "children": { "SubprocessEnvManager._take_step": { "total": 167.0148465180655, "count": 63341, "self": 7.425864935188656, "children": { "TorchPolicy.evaluate": { "total": 159.58898158287684, "count": 62579, "self": 159.58898158287684 } } }, "workers": { "total": 1.4015868319975198, "count": 63341, "self": 0.0, "children": { "worker_root": { "total": 3202.677290979286, "count": 63341, "is_parallel": true, "self": 1477.2135028101147, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005597770000349556, "count": 1, "is_parallel": true, "self": 0.00405614300234447, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015416269980050856, "count": 8, "is_parallel": true, "self": 0.0015416269980050856 } } }, "UnityEnvironment.step": { "total": 0.07836671199947887, "count": 1, "is_parallel": true, "self": 0.0006818960000600782, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005450509997899644, "count": 1, "is_parallel": true, "self": 0.0005450509997899644 }, "communicator.exchange": { "total": 0.07333590700000059, "count": 1, "is_parallel": true, "self": 0.07333590700000059 }, "steps_from_proto": { "total": 0.003803857999628235, "count": 1, "is_parallel": true, "self": 0.00041702099861140596, "children": { "_process_rank_one_or_two_observation": { "total": 0.003386837001016829, "count": 8, "is_parallel": true, "self": 0.003386837001016829 } } } } } } }, "UnityEnvironment.step": { "total": 1725.4637881691715, "count": 63340, "is_parallel": true, "self": 48.985426915158314, "children": { "UnityEnvironment._generate_step_input": { "total": 31.81300107500283, "count": 63340, "is_parallel": true, "self": 31.81300107500283 }, "communicator.exchange": { "total": 1496.9879256441163, "count": 63340, "is_parallel": true, "self": 1496.9879256441163 }, "steps_from_proto": { "total": 147.67743453489402, "count": 63340, "is_parallel": true, "self": 28.880269768150356, "children": { "_process_rank_one_or_two_observation": { "total": 118.79716476674366, "count": 506720, "is_parallel": true, "self": 118.79716476674366 } } } } } } } } } } }, "trainer_advance": { "total": 1123.0684376521167, "count": 63341, "self": 4.161758658353392, "children": { "process_trajectory": { "total": 162.39191353976275, "count": 63341, "self": 161.90326020276189, "children": { "RLTrainer._checkpoint": { "total": 0.4886533370008692, "count": 2, "self": 0.4886533370008692 } } }, "_update_policy": { "total": 956.5147654540006, "count": 434, "self": 378.30292891700356, "children": { "TorchPPOOptimizer.update": { "total": 578.211836536997, "count": 22839, "self": 578.211836536997 } } } } } } }, "trainer_threads": { "total": 1.0390012903371826e-06, "count": 1, "self": 1.0390012903371826e-06 }, "TrainerController._save_models": { "total": 0.10121195400097349, "count": 1, "self": 0.004480802001125994, "children": { "RLTrainer._checkpoint": { "total": 0.0967311519998475, "count": 1, "self": 0.0967311519998475 } } } } } } }