{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.453093022108078, "min": 0.453093022108078, "max": 1.409125566482544, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 13455.05078125, "min": 13455.05078125, "max": 42747.234375, "count": 33 }, "Pyramids.Step.mean": { "value": 989961.0, "min": 29873.0, "max": 989961.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989961.0, "min": 29873.0, "max": 989961.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.3831951916217804, "min": -0.14299391210079193, "max": 0.48588743805885315, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 101.54672241210938, "min": -33.91477966308594, "max": 131.18960571289062, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.01485910639166832, "min": 0.011587546207010746, "max": 0.48251664638519287, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.9376633167266846, "min": 3.093874931335449, "max": 114.3564453125, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07046148653417865, "min": 0.06349505386708229, "max": 0.07229583929074393, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9864608114785012, "min": 0.5000051367608429, "max": 1.0287088412539258, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.013164488933286296, "min": 0.00018941111886884622, "max": 0.015993467040797918, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.18430284506600814, "min": 0.002272933426426155, "max": 0.22390853857117085, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.476097508000002e-06, "min": 7.476097508000002e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010466536511200003, "min": 0.00010466536511200003, "max": 0.0033312372895875995, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10249200000000003, "min": 0.10249200000000003, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4348880000000004, "min": 1.3886848, "max": 2.4019470000000007, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002589508000000001, "min": 0.0002589508000000001, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036253112000000014, "min": 0.0036253112000000014, "max": 0.11105019876000002, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01657802239060402, "min": 0.01657802239060402, "max": 0.4734252095222473, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.23209230601787567, "min": 0.23209230601787567, "max": 3.313976526260376, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 505.7894736842105, "min": 397.8974358974359, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28830.0, "min": 16800.0, "max": 32241.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.3908172073806155, "min": -0.9999125525355339, "max": 1.4995974432441252, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 80.6673980280757, "min": -31.997201681137085, "max": 118.4681980162859, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.3908172073806155, "min": -0.9999125525355339, "max": 1.4995974432441252, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 80.6673980280757, "min": -31.997201681137085, "max": 118.4681980162859, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.08623238031351979, "min": 0.07286444600211762, "max": 8.88130902192172, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 5.001478058184148, "min": 5.001478058184148, "max": 150.98225337266922, "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": "1741953933", "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 --force", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1741956111" }, "total": 2177.918342014, "count": 1, "self": 0.5826338179999766, "children": { "run_training.setup": { "total": 0.02030397799990169, "count": 1, "self": 0.02030397799990169 }, "TrainerController.start_learning": { "total": 2177.315404218, "count": 1, "self": 1.3315470610091324, "children": { "TrainerController._reset_env": { "total": 2.161311093999757, "count": 1, "self": 2.161311093999757 }, "TrainerController.advance": { "total": 2173.6783194319905, "count": 63456, "self": 1.3719382519466308, "children": { "env_step": { "total": 1489.093976970073, "count": 63456, "self": 1330.91040578393, "children": { "SubprocessEnvManager._take_step": { "total": 157.38387551717005, "count": 63456, "self": 4.768365410184288, "children": { "TorchPolicy.evaluate": { "total": 152.61551010698577, "count": 62556, "self": 152.61551010698577 } } }, "workers": { "total": 0.7996956689730723, "count": 63456, "self": 0.0, "children": { "worker_root": { "total": 2172.1009076298647, "count": 63456, "is_parallel": true, "self": 953.5645027409064, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002043379000042478, "count": 1, "is_parallel": true, "self": 0.0007203569998637249, "children": { "_process_rank_one_or_two_observation": { "total": 0.001323022000178753, "count": 8, "is_parallel": true, "self": 0.001323022000178753 } } }, "UnityEnvironment.step": { "total": 0.0747499809999681, "count": 1, "is_parallel": true, "self": 0.0005417870002020209, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004515489999903366, "count": 1, "is_parallel": true, "self": 0.0004515489999903366 }, "communicator.exchange": { "total": 0.07206241499989119, "count": 1, "is_parallel": true, "self": 0.07206241499989119 }, "steps_from_proto": { "total": 0.0016942299998845556, "count": 1, "is_parallel": true, "self": 0.0003574280003704189, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013368019995141367, "count": 8, "is_parallel": true, "self": 0.0013368019995141367 } } } } } } }, "UnityEnvironment.step": { "total": 1218.5364048889583, "count": 63455, "is_parallel": true, "self": 31.896653183194758, "children": { "UnityEnvironment._generate_step_input": { "total": 23.66034070299156, "count": 63455, "is_parallel": true, "self": 23.66034070299156 }, "communicator.exchange": { "total": 1065.1386385189348, "count": 63455, "is_parallel": true, "self": 1065.1386385189348 }, "steps_from_proto": { "total": 97.8407724838371, "count": 63455, "is_parallel": true, "self": 19.752610196371734, "children": { "_process_rank_one_or_two_observation": { "total": 78.08816228746537, "count": 507640, "is_parallel": true, "self": 78.08816228746537 } } } } } } } } } } }, "trainer_advance": { "total": 683.2124042099708, "count": 63456, "self": 2.5418236499981504, "children": { "process_trajectory": { "total": 127.98841752397175, "count": 63456, "self": 127.72404617297207, "children": { "RLTrainer._checkpoint": { "total": 0.26437135099968145, "count": 2, "self": 0.26437135099968145 } } }, "_update_policy": { "total": 552.6821630360009, "count": 446, "self": 303.04228856601276, "children": { "TorchPPOOptimizer.update": { "total": 249.63987446998817, "count": 22821, "self": 249.63987446998817 } } } } } } }, "trainer_threads": { "total": 1.302000782743562e-06, "count": 1, "self": 1.302000782743562e-06 }, "TrainerController._save_models": { "total": 0.14422532899970975, "count": 1, "self": 0.0038966459997027414, "children": { "RLTrainer._checkpoint": { "total": 0.140328683000007, "count": 1, "self": 0.140328683000007 } } } } } } }