{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5980753898620605, "min": 0.5977312326431274, "max": 1.455580472946167, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 18076.23046875, "min": 17711.97265625, "max": 44156.48828125, "count": 33 }, "Pyramids.Step.mean": { "value": 989988.0, "min": 29952.0, "max": 989988.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989988.0, "min": 29952.0, "max": 989988.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5569621324539185, "min": -0.08932052552700043, "max": 0.5974917411804199, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 154.27850341796875, "min": -21.70488739013672, "max": 165.50521850585938, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.012856355868279934, "min": -0.0037182506639510393, "max": 0.26933637261390686, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.5612106323242188, "min": -0.9890546798706055, "max": 64.91006469726562, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06615394833941189, "min": 0.06539315816813282, "max": 0.07410251796143305, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9261552767517666, "min": 0.5187176257300313, "max": 1.0349855727496713, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01428789512733818, "min": 0.000499329026805023, "max": 0.0158838480185973, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.20003053178273453, "min": 0.005991948321660276, "max": 0.23825772027895947, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.471318938164284e-06, "min": 7.471318938164284e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010459846513429998, "min": 0.00010459846513429998, "max": 0.0036332590889137, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10249040714285715, "min": 0.10249040714285715, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4348657, "min": 1.3886848, "max": 2.6110863, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0005078323878571426, "min": 0.0005078323878571426, "max": 0.019676870217142855, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.007109653429999997, "min": 0.007109653429999997, "max": 0.24223615136999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.011514542624354362, "min": 0.010997733101248741, "max": 0.48224401473999023, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.16120359301567078, "min": 0.15396825969219208, "max": 3.3757081031799316, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 361.41975308641975, "min": 331.0722891566265, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29275.0, "min": 15984.0, "max": 32667.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.613878990764971, "min": -1.0000000521540642, "max": 1.644826485090945, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 130.72419825196266, "min": -31.997201666235924, "max": 136.96419852226973, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.613878990764971, "min": -1.0000000521540642, "max": 1.644826485090945, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 130.72419825196266, "min": -31.997201666235924, "max": 136.96419852226973, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.042633562677368855, "min": 0.039631059686721794, "max": 9.502635225653648, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.4533185768668773, "min": 3.3300426969799446, "max": 152.04216361045837, "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": "1768176783", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/home/brennan/miniconda3/envs/hfrdl5/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=../training-envs-executables-linux/Pyramids/Pyramids/Pyramids --run-id=Pyramids_Training_V1 --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": "1768177890" }, "total": 1106.780502214001, "count": 1, "self": 0.27012374400146655, "children": { "run_training.setup": { "total": 0.01927483300005406, "count": 1, "self": 0.01927483300005406 }, "TrainerController.start_learning": { "total": 1106.4911036369995, "count": 1, "self": 1.0141862880345798, "children": { "TrainerController._reset_env": { "total": 1.7647473919996628, "count": 1, "self": 1.7647473919996628 }, "TrainerController.advance": { "total": 1103.6554809079662, "count": 63900, "self": 0.9437354757374123, "children": { "env_step": { "total": 712.1743585260347, "count": 63900, "self": 616.4118523037787, "children": { "SubprocessEnvManager._take_step": { "total": 95.11072628014881, "count": 63900, "self": 2.417274599227312, "children": { "TorchPolicy.evaluate": { "total": 92.6934516809215, "count": 62574, "self": 92.6934516809215 } } }, "workers": { "total": 0.6517799421071686, "count": 63900, "self": 0.0, "children": { "worker_root": { "total": 1105.2504435012406, "count": 63900, "is_parallel": true, "self": 550.0655208433373, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001305886000409373, "count": 1, "is_parallel": true, "self": 0.00037679599972761935, "children": { "_process_rank_one_or_two_observation": { "total": 0.0009290900006817537, "count": 8, "is_parallel": true, "self": 0.0009290900006817537 } } }, "UnityEnvironment.step": { "total": 0.024866629999451106, "count": 1, "is_parallel": true, "self": 0.00024464199941576226, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00021748299968749052, "count": 1, "is_parallel": true, "self": 0.00021748299968749052 }, "communicator.exchange": { "total": 0.023667555999963952, "count": 1, "is_parallel": true, "self": 0.023667555999963952 }, "steps_from_proto": { "total": 0.0007369490003839019, "count": 1, "is_parallel": true, "self": 0.00016332100130966865, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005736279990742332, "count": 8, "is_parallel": true, "self": 0.0005736279990742332 } } } } } } }, "UnityEnvironment.step": { "total": 555.1849226579034, "count": 63899, "is_parallel": true, "self": 15.358814169449943, "children": { "UnityEnvironment._generate_step_input": { "total": 10.183706354170681, "count": 63899, "is_parallel": true, "self": 10.183706354170681 }, "communicator.exchange": { "total": 489.5795271151692, "count": 63899, "is_parallel": true, "self": 489.5795271151692 }, "steps_from_proto": { "total": 40.06287501911356, "count": 63899, "is_parallel": true, "self": 8.302330181147227, "children": { "_process_rank_one_or_two_observation": { "total": 31.760544837966336, "count": 511192, "is_parallel": true, "self": 31.760544837966336 } } } } } } } } } } }, "trainer_advance": { "total": 390.5373869061941, "count": 63900, "self": 1.9104905542635606, "children": { "process_trajectory": { "total": 74.50072235993684, "count": 63900, "self": 74.36048692793702, "children": { "RLTrainer._checkpoint": { "total": 0.1402354319998267, "count": 2, "self": 0.1402354319998267 } } }, "_update_policy": { "total": 314.1261739919937, "count": 454, "self": 180.22306276201653, "children": { "TorchPPOOptimizer.update": { "total": 133.90311122997718, "count": 22779, "self": 133.90311122997718 } } } } } } }, "trainer_threads": { "total": 6.199989002197981e-07, "count": 1, "self": 6.199989002197981e-07 }, "TrainerController._save_models": { "total": 0.0566884290001326, "count": 1, "self": 0.0012068039995938307, "children": { "RLTrainer._checkpoint": { "total": 0.05548162500053877, "count": 1, "self": 0.05548162500053877 } } } } } } }