{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5882905125617981, "min": 0.5882905125617981, "max": 1.4445035457611084, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 17705.19140625, "min": 17705.19140625, "max": 43820.4609375, "count": 33 }, "Pyramids.Step.mean": { "value": 989958.0, "min": 29952.0, "max": 989958.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989958.0, "min": 29952.0, "max": 989958.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.19378341734409332, "min": -0.09713666886091232, "max": 0.32777920365333557, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 49.22098922729492, "min": -23.312801361083984, "max": 84.56703186035156, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.30712687969207764, "min": -0.4465263783931732, "max": 0.778298556804657, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -78.0102310180664, "min": -115.65032958984375, "max": 184.45675659179688, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06753586639194613, "min": 0.06624800781125241, "max": 0.07580704509421314, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9455021294872458, "min": 0.512265932213665, "max": 1.061762715592825, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01853889180707045, "min": 8.666716704617517e-05, "max": 0.035699201114766765, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2595444852989863, "min": 0.0012133403386464523, "max": 0.4997888156067347, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.44860466002143e-06, "min": 7.44860466002143e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010428046524030002, "min": 0.00010428046524030002, "max": 0.0033828749723751007, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10248283571428574, "min": 0.10248283571428574, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4347597000000003, "min": 1.3691136000000002, "max": 2.5276249000000006, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002580352878571429, "min": 0.0002580352878571429, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036124940300000007, "min": 0.0036124940300000007, "max": 0.11278972751, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.011106963269412518, "min": 0.011106963269412518, "max": 0.6607980728149414, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1554974913597107, "min": 0.1554974913597107, "max": 4.62558650970459, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 608.5217391304348, "min": 531.1509433962265, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 27992.0, "min": 15984.0, "max": 32649.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.8695782290204711, "min": -1.0000000521540642, "max": 1.2100481197789863, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 40.00059853494167, "min": -32.000001668930054, "max": 65.34259846806526, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.8695782290204711, "min": -1.0000000521540642, "max": 1.2100481197789863, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 40.00059853494167, "min": -32.000001668930054, "max": 65.34259846806526, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.07021384063061661, "min": 0.06812311311174805, "max": 14.008263183757663, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.229836669008364, "min": 3.229836669008364, "max": 224.1322109401226, "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": "1716961548", "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": "2.3.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1716963817" }, "total": 2269.1189995590003, "count": 1, "self": 0.49157672700039257, "children": { "run_training.setup": { "total": 0.05864394899998615, "count": 1, "self": 0.05864394899998615 }, "TrainerController.start_learning": { "total": 2268.568778883, "count": 1, "self": 1.8625474419845887, "children": { "TrainerController._reset_env": { "total": 3.2071996079999963, "count": 1, "self": 3.2071996079999963 }, "TrainerController.advance": { "total": 2263.4090639290157, "count": 63293, "self": 1.9481654989808703, "children": { "env_step": { "total": 1594.0946936410244, "count": 63293, "self": 1428.9048318720334, "children": { "SubprocessEnvManager._take_step": { "total": 164.03504797097816, "count": 63293, "self": 5.8489514269800225, "children": { "TorchPolicy.evaluate": { "total": 158.18609654399813, "count": 62552, "self": 158.18609654399813 } } }, "workers": { "total": 1.1548137980128104, "count": 63293, "self": 0.0, "children": { "worker_root": { "total": 2262.2840666509446, "count": 63293, "is_parallel": true, "self": 982.955389554973, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005019709999999122, "count": 1, "is_parallel": true, "self": 0.0034935729999574505, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015261370000416719, "count": 8, "is_parallel": true, "self": 0.0015261370000416719 } } }, "UnityEnvironment.step": { "total": 0.048932879999995293, "count": 1, "is_parallel": true, "self": 0.0006687089999672935, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005017729999963194, "count": 1, "is_parallel": true, "self": 0.0005017729999963194 }, "communicator.exchange": { "total": 0.04589852399999472, "count": 1, "is_parallel": true, "self": 0.04589852399999472 }, "steps_from_proto": { "total": 0.001863874000036958, "count": 1, "is_parallel": true, "self": 0.00038676999992048877, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014771040001164693, "count": 8, "is_parallel": true, "self": 0.0014771040001164693 } } } } } } }, "UnityEnvironment.step": { "total": 1279.3286770959717, "count": 63292, "is_parallel": true, "self": 38.96720433284827, "children": { "UnityEnvironment._generate_step_input": { "total": 26.104903243049932, "count": 63292, "is_parallel": true, "self": 26.104903243049932 }, "communicator.exchange": { "total": 1102.0334595860165, "count": 63292, "is_parallel": true, "self": 1102.0334595860165 }, "steps_from_proto": { "total": 112.22310993405688, "count": 63292, "is_parallel": true, "self": 24.23261198010522, "children": { "_process_rank_one_or_two_observation": { "total": 87.99049795395166, "count": 506336, "is_parallel": true, "self": 87.99049795395166 } } } } } } } } } } }, "trainer_advance": { "total": 667.3662047890106, "count": 63293, "self": 3.3630484290450795, "children": { "process_trajectory": { "total": 138.291096423966, "count": 63293, "self": 137.9474408289658, "children": { "RLTrainer._checkpoint": { "total": 0.34365559500020026, "count": 2, "self": 0.34365559500020026 } } }, "_update_policy": { "total": 525.7120599359995, "count": 441, "self": 311.2895666680187, "children": { "TorchPPOOptimizer.update": { "total": 214.42249326798077, "count": 22830, "self": 214.42249326798077 } } } } } } }, "trainer_threads": { "total": 1.0200001270277426e-06, "count": 1, "self": 1.0200001270277426e-06 }, "TrainerController._save_models": { "total": 0.08996688399975028, "count": 1, "self": 0.0015897059997769247, "children": { "RLTrainer._checkpoint": { "total": 0.08837717799997336, "count": 1, "self": 0.08837717799997336 } } } } } } }