{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.44988521933555603, "min": 0.44988521933555603, "max": 1.343063473701477, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 13431.7734375, "min": 13431.7734375, "max": 40743.171875, "count": 33 }, "Pyramids.Step.mean": { "value": 989940.0, "min": 29952.0, "max": 989940.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989940.0, "min": 29952.0, "max": 989940.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.27387765049934387, "min": -0.11215900629758835, "max": 0.34999924898147583, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 71.20819091796875, "min": -27.366798400878906, "max": 91.6998062133789, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.018822114914655685, "min": -0.006025300361216068, "max": 0.32082539796829224, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 4.893749713897705, "min": -1.5424768924713135, "max": 77.31892395019531, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06813016949208937, "min": 0.06676529514134884, "max": 0.07683899558667116, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9538223728892513, "min": 0.49243120230425247, "max": 1.0954655726156632, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.012273429528007812, "min": 0.0003360713871863572, "max": 0.013485765404593189, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.17182801339210937, "min": 0.004032856646236286, "max": 0.18880071566430465, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.445476089635708e-06, "min": 7.445476089635708e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010423666525489991, "min": 0.00010423666525489991, "max": 0.0036336748887751, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10248179285714287, "min": 0.10248179285714287, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4347451000000002, "min": 1.3886848, "max": 2.6112249000000003, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002579311064285713, "min": 0.0002579311064285713, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003611035489999998, "min": 0.003611035489999998, "max": 0.12114136750999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.011485259048640728, "min": 0.011485259048640728, "max": 0.48839521408081055, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.16079363226890564, "min": 0.16079363226890564, "max": 3.418766498565674, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 530.2372881355932, "min": 494.8545454545455, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31284.0, "min": 15984.0, "max": 32876.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.1306542050787958, "min": -1.0000000521540642, "max": 1.286898150904612, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 66.70859809964895, "min": -30.388601690530777, "max": 70.77939829975367, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.1306542050787958, "min": -1.0000000521540642, "max": 1.286898150904612, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 66.70859809964895, "min": -30.388601690530777, "max": 70.77939829975367, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.0639118926335221, "min": 0.0639118926335221, "max": 9.038941427133977, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.770801665377803, "min": 3.619523533481697, "max": 144.62306283414364, "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": "1705574866", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.2+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1705582015" }, "total": 7149.486083071999, "count": 1, "self": 0.6582111179995991, "children": { "run_training.setup": { "total": 0.07413246400005846, "count": 1, "self": 0.07413246400005846 }, "TrainerController.start_learning": { "total": 7148.753739489999, "count": 1, "self": 2.2776394770462502, "children": { "TrainerController._reset_env": { "total": 5.452702811000108, "count": 1, "self": 5.452702811000108 }, "TrainerController.advance": { "total": 7136.434403611954, "count": 63480, "self": 2.6938098918089963, "children": { "env_step": { "total": 2412.863850204035, "count": 63480, "self": 1980.441483072164, "children": { "SubprocessEnvManager._take_step": { "total": 430.95979879287574, "count": 63480, "self": 8.38727602504423, "children": { "TorchPolicy.evaluate": { "total": 422.5725227678315, "count": 62558, "self": 422.5725227678315 } } }, "workers": { "total": 1.4625683389951973, "count": 63480, "self": 0.0, "children": { "worker_root": { "total": 7136.556129124882, "count": 63480, "is_parallel": true, "self": 5338.920364959773, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.010066795000057027, "count": 1, "is_parallel": true, "self": 0.005315205999977479, "children": { "_process_rank_one_or_two_observation": { "total": 0.004751589000079548, "count": 8, "is_parallel": true, "self": 0.004751589000079548 } } }, "UnityEnvironment.step": { "total": 0.06761646400013888, "count": 1, "is_parallel": true, "self": 0.0007668360001389374, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005318949999946199, "count": 1, "is_parallel": true, "self": 0.0005318949999946199 }, "communicator.exchange": { "total": 0.06412648800005627, "count": 1, "is_parallel": true, "self": 0.06412648800005627 }, "steps_from_proto": { "total": 0.002191244999949049, "count": 1, "is_parallel": true, "self": 0.0004251149996434833, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017661300003055658, "count": 8, "is_parallel": true, "self": 0.0017661300003055658 } } } } } } }, "UnityEnvironment.step": { "total": 1797.6357641651089, "count": 63479, "is_parallel": true, "self": 50.54104356325888, "children": { "UnityEnvironment._generate_step_input": { "total": 29.034552103734768, "count": 63479, "is_parallel": true, "self": 29.034552103734768 }, "communicator.exchange": { "total": 1584.355912022159, "count": 63479, "is_parallel": true, "self": 1584.355912022159 }, "steps_from_proto": { "total": 133.7042564759563, "count": 63479, "is_parallel": true, "self": 28.44822761267028, "children": { "_process_rank_one_or_two_observation": { "total": 105.25602886328602, "count": 507832, "is_parallel": true, "self": 105.25602886328602 } } } } } } } } } } }, "trainer_advance": { "total": 4720.87674351611, "count": 63480, "self": 4.913897611234461, "children": { "process_trajectory": { "total": 341.0230255228828, "count": 63480, "self": 339.3154740928833, "children": { "RLTrainer._checkpoint": { "total": 1.707551429999512, "count": 2, "self": 1.707551429999512 } } }, "_update_policy": { "total": 4374.939820381993, "count": 453, "self": 394.9948957160209, "children": { "TorchPPOOptimizer.update": { "total": 3979.944924665972, "count": 22785, "self": 3979.944924665972 } } } } } } }, "trainer_threads": { "total": 1.0009989637183025e-06, "count": 1, "self": 1.0009989637183025e-06 }, "TrainerController._save_models": { "total": 4.588992589000554, "count": 1, "self": 0.019022479000341264, "children": { "RLTrainer._checkpoint": { "total": 4.569970110000213, "count": 1, "self": 4.569970110000213 } } } } } } }