{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.44491201639175415, "min": 0.4208064675331116, "max": 1.5236198902130127, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 13283.29296875, "min": 12556.865234375, "max": 46220.53125, "count": 33 }, "Pyramids.Step.mean": { "value": 989972.0, "min": 29952.0, "max": 989972.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989972.0, "min": 29952.0, "max": 989972.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.3741862177848816, "min": -0.11141247302293777, "max": 0.3741862177848816, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 99.15934753417969, "min": -26.816795349121094, "max": 99.15934753417969, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.27242928743362427, "min": -0.30325859785079956, "max": 0.3844088017940521, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 72.19376373291016, "min": -77.93746185302734, "max": 100.71510314941406, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06969957315032767, "min": 0.06518241845078489, "max": 0.0740373770781194, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.045493597254915, "min": 0.4748150976846428, "max": 1.0716219201008332, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.019208254186501968, "min": 0.0008947574516578548, "max": 0.02849102554884869, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2881238127975295, "min": 0.009571329274111593, "max": 0.4273653832327303, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.497057501013333e-06, "min": 7.497057501013333e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011245586251519999, "min": 0.00011245586251519999, "max": 0.0032579105140298995, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10249898666666667, "min": 0.10249898666666667, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5374848, "min": 1.3886848, "max": 2.4433441000000005, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025964876800000004, "min": 0.00025964876800000004, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0038947315200000003, "min": 0.0038947315200000003, "max": 0.10861841299000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.012915009632706642, "min": 0.012915009632706642, "max": 0.2748355269432068, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.19372513890266418, "min": 0.191584050655365, "max": 1.9238487482070923, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 472.7368421052632, "min": 454.3636363636364, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 26946.0, "min": 15984.0, "max": 32657.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.4570736607961488, "min": -1.0000000521540642, "max": 1.4570736607961488, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 83.05319866538048, "min": -30.689001724123955, "max": 83.05319866538048, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.4570736607961488, "min": -1.0000000521540642, "max": 1.4570736607961488, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 83.05319866538048, "min": -30.689001724123955, "max": 83.05319866538048, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.06347222718218211, "min": 0.06347222718218211, "max": 4.778371950611472, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.61791694938438, "min": 3.61791694938438, "max": 76.45395120978355, "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": "1785329791", "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", "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": "1785332164" }, "total": 2372.874874849, "count": 1, "self": 0.5381917090003299, "children": { "run_training.setup": { "total": 0.03608406899991223, "count": 1, "self": 0.03608406899991223 }, "TrainerController.start_learning": { "total": 2372.300599071, "count": 1, "self": 1.51999130895274, "children": { "TrainerController._reset_env": { "total": 3.396483885000066, "count": 1, "self": 3.396483885000066 }, "TrainerController.advance": { "total": 2367.306364806047, "count": 63498, "self": 1.5186678941158789, "children": { "env_step": { "total": 1723.0713855499203, "count": 63498, "self": 1561.833898415865, "children": { "SubprocessEnvManager._take_step": { "total": 160.32945618400322, "count": 63498, "self": 4.886435731017173, "children": { "TorchPolicy.evaluate": { "total": 155.44302045298605, "count": 62554, "self": 155.44302045298605 } } }, "workers": { "total": 0.9080309500519661, "count": 63498, "self": 0.0, "children": { "worker_root": { "total": 2366.6112497779977, "count": 63498, "is_parallel": true, "self": 929.0450879780667, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005636097999968115, "count": 1, "is_parallel": true, "self": 0.004292541999802779, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013435560001653357, "count": 8, "is_parallel": true, "self": 0.0013435560001653357 } } }, "UnityEnvironment.step": { "total": 0.05330870500006313, "count": 1, "is_parallel": true, "self": 0.0006378859998221742, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004989790000990979, "count": 1, "is_parallel": true, "self": 0.0004989790000990979 }, "communicator.exchange": { "total": 0.05042960800005858, "count": 1, "is_parallel": true, "self": 0.05042960800005858 }, "steps_from_proto": { "total": 0.001742232000083277, "count": 1, "is_parallel": true, "self": 0.0003491079999093927, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013931240001738843, "count": 8, "is_parallel": true, "self": 0.0013931240001738843 } } } } } } }, "UnityEnvironment.step": { "total": 1437.566161799931, "count": 63497, "is_parallel": true, "self": 35.96094545489882, "children": { "UnityEnvironment._generate_step_input": { "total": 24.510611747957228, "count": 63497, "is_parallel": true, "self": 24.510611747957228 }, "communicator.exchange": { "total": 1262.9806272209935, "count": 63497, "is_parallel": true, "self": 1262.9806272209935 }, "steps_from_proto": { "total": 114.11397737608138, "count": 63497, "is_parallel": true, "self": 23.852097425277975, "children": { "_process_rank_one_or_two_observation": { "total": 90.2618799508034, "count": 507976, "is_parallel": true, "self": 90.2618799508034 } } } } } } } } } } }, "trainer_advance": { "total": 642.7163113620107, "count": 63498, "self": 2.823891507048984, "children": { "process_trajectory": { "total": 115.51558385796125, "count": 63498, "self": 115.25609237196113, "children": { "RLTrainer._checkpoint": { "total": 0.2594914860001154, "count": 2, "self": 0.2594914860001154 } } }, "_update_policy": { "total": 524.3768359970005, "count": 444, "self": 280.7999011279644, "children": { "TorchPPOOptimizer.update": { "total": 243.5769348690361, "count": 22797, "self": 243.5769348690361 } } } } } } }, "trainer_threads": { "total": 8.199999683711212e-07, "count": 1, "self": 8.199999683711212e-07 }, "TrainerController._save_models": { "total": 0.07775825099997746, "count": 1, "self": 0.0010763279997263453, "children": { "RLTrainer._checkpoint": { "total": 0.07668192300025112, "count": 1, "self": 0.07668192300025112 } } } } } } }