{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4006115794181824, "min": 0.4006115794181824, "max": 1.4487403631210327, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 12114.494140625, "min": 12114.494140625, "max": 43948.98828125, "count": 33 }, "Pyramids.Step.mean": { "value": 989903.0, "min": 29952.0, "max": 989903.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989903.0, "min": 29952.0, "max": 989903.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.620914101600647, "min": -0.11833567917346954, "max": 0.620914101600647, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 175.71868896484375, "min": -28.518898010253906, "max": 175.71868896484375, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.01589723862707615, "min": -0.008096341975033283, "max": 0.6263262033462524, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 4.498918533325195, "min": -2.2426867485046387, "max": 148.43931579589844, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07026300107738007, "min": 0.06699870670200354, "max": 0.0731597768345568, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.053945016160701, "min": 0.47233068235934417, "max": 1.053945016160701, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016183158391485528, "min": 0.0006199020646915053, "max": 0.02634335217676596, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2427473758722829, "min": 0.007593449112245326, "max": 0.2427473758722829, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.591137469653336e-06, "min": 7.591137469653336e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011386706204480004, "min": 0.00011386706204480004, "max": 0.0035070581309806998, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10253034666666666, "min": 0.10253034666666666, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5379551999999999, "min": 1.3691136000000002, "max": 2.5690193000000003, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002627816320000001, "min": 0.0002627816320000001, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003941724480000001, "min": 0.003941724480000001, "max": 0.11692502807000002, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.012456548400223255, "min": 0.012128330767154694, "max": 0.6615239977836609, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1868482232093811, "min": 0.1697966307401657, "max": 4.6306681632995605, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 284.46078431372547, "min": 284.46078431372547, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29015.0, "min": 15984.0, "max": 32214.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.676313707349347, "min": -1.0000000521540642, "max": 1.676313707349347, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 170.9839981496334, "min": -32.000001668930054, "max": 170.9839981496334, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.676313707349347, "min": -1.0000000521540642, "max": 1.676313707349347, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 170.9839981496334, "min": -32.000001668930054, "max": 170.9839981496334, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.036582575976728336, "min": 0.036582575976728336, "max": 16.011247418820858, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.73142274962629, "min": 3.73142274962629, "max": 256.1799587011337, "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": "1762574907", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/home/mahir_05/.local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids1 --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": "1762577888" }, "total": 2981.2942023530004, "count": 1, "self": 0.6380895160004911, "children": { "run_training.setup": { "total": 0.042454750999695534, "count": 1, "self": 0.042454750999695534 }, "TrainerController.start_learning": { "total": 2980.613658086, "count": 1, "self": 1.9238535701247201, "children": { "TrainerController._reset_env": { "total": 2.301371091999954, "count": 1, "self": 2.301371091999954 }, "TrainerController.advance": { "total": 2976.1956813478755, "count": 63857, "self": 2.0625983546919997, "children": { "env_step": { "total": 2074.502175080065, "count": 63857, "self": 1940.326829040962, "children": { "SubprocessEnvManager._take_step": { "total": 132.96984455608026, "count": 63857, "self": 6.4471136642769125, "children": { "TorchPolicy.evaluate": { "total": 126.52273089180335, "count": 62559, "self": 126.52273089180335 } } }, "workers": { "total": 1.2055014830229993, "count": 63857, "self": 0.0, "children": { "worker_root": { "total": 2977.1734389599715, "count": 63857, "is_parallel": true, "self": 1178.2878349099847, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.003136372999961168, "count": 1, "is_parallel": true, "self": 0.0009768170007191657, "children": { "_process_rank_one_or_two_observation": { "total": 0.002159555999242002, "count": 8, "is_parallel": true, "self": 0.002159555999242002 } } }, "UnityEnvironment.step": { "total": 0.051126385999850754, "count": 1, "is_parallel": true, "self": 0.0009537919995636912, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005114900000080524, "count": 1, "is_parallel": true, "self": 0.0005114900000080524 }, "communicator.exchange": { "total": 0.04804880400024558, "count": 1, "is_parallel": true, "self": 0.04804880400024558 }, "steps_from_proto": { "total": 0.0016123000000334287, "count": 1, "is_parallel": true, "self": 0.0002869120007744641, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013253879992589646, "count": 8, "is_parallel": true, "self": 0.0013253879992589646 } } } } } } }, "UnityEnvironment.step": { "total": 1798.8856040499868, "count": 63856, "is_parallel": true, "self": 40.246833711026284, "children": { "UnityEnvironment._generate_step_input": { "total": 27.425078970020422, "count": 63856, "is_parallel": true, "self": 27.425078970020422 }, "communicator.exchange": { "total": 1620.419164923011, "count": 63856, "is_parallel": true, "self": 1620.419164923011 }, "steps_from_proto": { "total": 110.79452644592902, "count": 63856, "is_parallel": true, "self": 23.184956930960197, "children": { "_process_rank_one_or_two_observation": { "total": 87.60956951496883, "count": 510848, "is_parallel": true, "self": 87.60956951496883 } } } } } } } } } } }, "trainer_advance": { "total": 899.6309079131183, "count": 63857, "self": 3.5009336571065433, "children": { "process_trajectory": { "total": 147.96270269602337, "count": 63857, "self": 147.6640406800243, "children": { "RLTrainer._checkpoint": { "total": 0.2986620159990707, "count": 2, "self": 0.2986620159990707 } } }, "_update_policy": { "total": 748.1672715599884, "count": 445, "self": 341.89849008807914, "children": { "TorchPPOOptimizer.update": { "total": 406.2687814719093, "count": 22860, "self": 406.2687814719093 } } } } } } }, "trainer_threads": { "total": 3.424999704293441e-06, "count": 1, "self": 3.424999704293441e-06 }, "TrainerController._save_models": { "total": 0.19274865100032912, "count": 1, "self": 0.002116960000421386, "children": { "RLTrainer._checkpoint": { "total": 0.19063169099990773, "count": 1, "self": 0.19063169099990773 } } } } } } }