{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.9874333143234253, "min": 0.9874333143234253, "max": 1.390523076057434, "count": 3 }, "Pyramids.Policy.Entropy.sum": { "value": 29954.77734375, "min": 25096.16015625, "max": 33246.4453125, "count": 3 }, "Pyramids.Step.mean": { "value": 89975.0, "min": 29895.0, "max": 89975.0, "count": 3 }, "Pyramids.Step.sum": { "value": 89975.0, "min": 29895.0, "max": 89975.0, "count": 3 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": -0.05904434248805046, "min": -0.05904434248805046, "max": 0.06711149215698242, "count": 3 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": -14.111598014831543, "min": -14.111598014831543, "max": 9.46272087097168, "count": 3 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.14399568736553192, "min": 0.14399568736553192, "max": 0.26816484332084656, "count": 3 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 34.41497039794922, "min": 34.41497039794922, "max": 57.54234313964844, "count": 3 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06970529433140599, "min": 0.06970529433140599, "max": 0.07023294703085216, "count": 3 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.7667582376454658, "min": 0.28093178812340863, "max": 0.8402003982421108, "count": 3 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.002323954420249768, "min": 0.0010917167034284112, "max": 0.003567637713531831, "count": 3 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.025563498622747448, "min": 0.013100600441140935, "max": 0.025563498622747448, "count": 3 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.55283475511818e-05, "min": 7.55283475511818e-05, "max": 0.0002355135214955, "count": 3 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0008308118230629999, "min": 0.0008308118230629999, "max": 0.001998042533986, "count": 3 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1251760909090909, "min": 0.1251760909090909, "max": 0.1785045, "count": 3 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.376937, "min": 0.714018, "max": 1.866014, "count": 3 }, "Pyramids.Policy.Beta.mean": { "value": 0.0025250914818181823, "min": 0.0025250914818181823, "max": 0.00785259955, "count": 3 }, "Pyramids.Policy.Beta.sum": { "value": 0.027776006300000003, "min": 0.027776006300000003, "max": 0.0666547986, "count": 3 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.1162843257188797, "min": 0.1162843257188797, "max": 0.3269945979118347, "count": 3 }, "Pyramids.Losses.RNDLoss.sum": { "value": 1.279127597808838, "min": 1.279127597808838, "max": 2.1166720390319824, "count": 3 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 973.1578947368421, "min": 971.4375, "max": 982.09375, "count": 3 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 18490.0, "min": 15543.0, "max": 31427.0, "count": 3 }, "Pyramids.Environment.CumulativeReward.mean": { "value": -0.690685765019485, "min": -0.9151933838923773, "max": -0.690685765019485, "count": 3 }, "Pyramids.Environment.CumulativeReward.sum": { "value": -14.504401065409184, "min": -27.455801516771317, "max": -13.558000810444355, "count": 3 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": -0.690685765019485, "min": -0.9151933838923773, "max": -0.690685765019485, "count": 3 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": -14.504401065409184, "min": -27.455801516771317, "max": -13.558000810444355, "count": 3 }, "Pyramids.Policy.RndReward.mean": { "value": 1.2869210395784605, "min": 1.2869210395784605, "max": 3.9050290873274207, "count": 3 }, "Pyramids.Policy.RndReward.sum": { "value": 27.02534183114767, "min": 27.02534183114767, "max": 62.48046539723873, "count": 3 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 3 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 3 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1785710188", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/content/miniconda3/envs/mlagents/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=PyramidsTraining --no-graphics --resume", "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": "1785710380" }, "total": 191.47977757600006, "count": 1, "self": 0.4870674460000828, "children": { "run_training.setup": { "total": 0.02495836100001725, "count": 1, "self": 0.02495836100001725 }, "TrainerController.start_learning": { "total": 190.96775176899996, "count": 1, "self": 0.16547899999704896, "children": { "TrainerController._reset_env": { "total": 1.9003750419999506, "count": 1, "self": 1.9003750419999506 }, "TrainerController.advance": { "total": 188.7022394200028, "count": 5524, "self": 0.14250821000223368, "children": { "env_step": { "total": 129.70385443400028, "count": 5524, "self": 119.24366140600296, "children": { "SubprocessEnvManager._take_step": { "total": 10.353977096993958, "count": 5524, "self": 0.3739870309984781, "children": { "TorchPolicy.evaluate": { "total": 9.97999006599548, "count": 5512, "self": 9.97999006599548 } } }, "workers": { "total": 0.10621593100336213, "count": 5524, "self": 0.0, "children": { "worker_root": { "total": 190.09633259700445, "count": 5524, "is_parallel": true, "self": 83.11596902801512, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001667319000034695, "count": 1, "is_parallel": true, "self": 0.00044745099967258284, "children": { "_process_rank_one_or_two_observation": { "total": 0.001219868000362112, "count": 8, "is_parallel": true, "self": 0.001219868000362112 } } }, "UnityEnvironment.step": { "total": 0.06563532699988173, "count": 1, "is_parallel": true, "self": 0.0005493699998169177, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005239499998879182, "count": 1, "is_parallel": true, "self": 0.0005239499998879182 }, "communicator.exchange": { "total": 0.0629012680001324, "count": 1, "is_parallel": true, "self": 0.0629012680001324 }, "steps_from_proto": { "total": 0.0016607390000444866, "count": 1, "is_parallel": true, "self": 0.000396350999835704, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012643880002087826, "count": 8, "is_parallel": true, "self": 0.0012643880002087826 } } } } } } }, "UnityEnvironment.step": { "total": 106.98036356898933, "count": 5523, "is_parallel": true, "self": 2.912333767992777, "children": { "UnityEnvironment._generate_step_input": { "total": 2.0521974249904815, "count": 5523, "is_parallel": true, "self": 2.0521974249904815 }, "communicator.exchange": { "total": 93.46560114300541, "count": 5523, "is_parallel": true, "self": 93.46560114300541 }, "steps_from_proto": { "total": 8.550231233000659, "count": 5523, "is_parallel": true, "self": 1.9543746419819854, "children": { "_process_rank_one_or_two_observation": { "total": 6.5958565910186735, "count": 44184, "is_parallel": true, "self": 6.5958565910186735 } } } } } } } } } } }, "trainer_advance": { "total": 58.85587677600029, "count": 5524, "self": 0.25042941400056407, "children": { "process_trajectory": { "total": 8.570048295999413, "count": 5524, "self": 8.570048295999413 }, "_update_policy": { "total": 50.03539906600031, "count": 31, "self": 20.03511814899889, "children": { "TorchPPOOptimizer.update": { "total": 30.00028091700142, "count": 1989, "self": 30.00028091700142 } } } } } } }, "trainer_threads": { "total": 9.290001798945013e-07, "count": 1, "self": 9.290001798945013e-07 }, "TrainerController._save_models": { "total": 0.1996573779999835, "count": 1, "self": 0.01461410000001706, "children": { "RLTrainer._checkpoint": { "total": 0.18504327799996645, "count": 1, "self": 0.18504327799996645 } } } } } } }