{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 1.2222906351089478, "min": 1.2222906351089478, "max": 1.4934016466140747, "count": 3 }, "Pyramids.Policy.Entropy.sum": { "value": 36610.05078125, "min": 36610.05078125, "max": 45303.83203125, "count": 3 }, "Pyramids.Step.mean": { "value": 89904.0, "min": 29952.0, "max": 89904.0, "count": 3 }, "Pyramids.Step.sum": { "value": 89904.0, "min": 29952.0, "max": 89904.0, "count": 3 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": -0.08288588374853134, "min": -0.08288588374853134, "max": 0.14689230918884277, "count": 3 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": -19.89261245727539, "min": -19.89261245727539, "max": 34.8134765625, "count": 3 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.1430296003818512, "min": 0.1430296003818512, "max": 0.3020160496234894, "count": 3 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 34.32710266113281, "min": 34.32710266113281, "max": 71.57780456542969, "count": 3 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06946442895089551, "min": 0.06946442895089551, "max": 0.07239485042711527, "count": 3 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.7641087184598506, "min": 0.5067639529898069, "max": 0.7641087184598506, "count": 3 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.001176756660251799, "min": 0.001176756660251799, "max": 0.008866136739944838, "count": 3 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.012944323262769787, "min": 0.012944323262769787, "max": 0.06206295717961387, "count": 3 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.935907354699999e-05, "min": 7.935907354699999e-05, "max": 0.0002515063018788571, "count": 3 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0008729498090169999, "min": 0.0008729498090169999, "max": 0.0017605441131519997, "count": 3 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.12645299999999998, "min": 0.12645299999999998, "max": 0.1838354285714286, "count": 3 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.3909829999999999, "min": 1.2868480000000002, "max": 1.5457850000000002, "count": 3 }, "Pyramids.Policy.Beta.mean": { "value": 0.0026526546999999998, "min": 0.0026526546999999998, "max": 0.008385159314285713, "count": 3 }, "Pyramids.Policy.Beta.sum": { "value": 0.029179201699999997, "min": 0.029179201699999997, "max": 0.058696115199999996, "count": 3 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.09528748691082001, "min": 0.09528748691082001, "max": 0.43596264719963074, "count": 3 }, "Pyramids.Losses.RNDLoss.sum": { "value": 1.0481623411178589, "min": 1.0481623411178589, "max": 3.0517385005950928, "count": 3 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 997.96875, "min": 978.9090909090909, "max": 999.0, "count": 3 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31935.0, "min": 15984.0, "max": 32304.0, "count": 3 }, "Pyramids.Environment.CumulativeReward.mean": { "value": -0.9364125535357744, "min": -1.0000000521540642, "max": -0.8586364169463967, "count": 3 }, "Pyramids.Environment.CumulativeReward.sum": { "value": -29.96520171314478, "min": -29.96520171314478, "max": -16.000000834465027, "count": 3 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": -0.9364125535357744, "min": -1.0000000521540642, "max": -0.8586364169463967, "count": 3 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": -29.96520171314478, "min": -29.96520171314478, "max": -16.000000834465027, "count": 3 }, "Pyramids.Policy.RndReward.mean": { "value": 1.056591082829982, "min": 1.056591082829982, "max": 9.362661285325885, "count": 3 }, "Pyramids.Policy.RndReward.sum": { "value": 33.810914650559425, "min": 33.810914650559425, "max": 149.80258056521416, "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": "1715891893", "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": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1715892084" }, "total": 191.042960796, "count": 1, "self": 0.4808109269997658, "children": { "run_training.setup": { "total": 0.050715366000076756, "count": 1, "self": 0.050715366000076756 }, "TrainerController.start_learning": { "total": 190.51143450300015, "count": 1, "self": 0.11614303098735945, "children": { "TrainerController._reset_env": { "total": 2.189684550000038, "count": 1, "self": 2.189684550000038 }, "TrainerController.advance": { "total": 188.0940757430128, "count": 6261, "self": 0.12312778002842606, "children": { "env_step": { "total": 124.53421188299285, "count": 6261, "self": 112.16764932098795, "children": { "SubprocessEnvManager._take_step": { "total": 12.289096521010833, "count": 6261, "self": 0.4617249660198013, "children": { "TorchPolicy.evaluate": { "total": 11.827371554991032, "count": 6256, "self": 11.827371554991032 } } }, "workers": { "total": 0.07746604099406795, "count": 6261, "self": 0.0, "children": { "worker_root": { "total": 189.90739130198813, "count": 6261, "is_parallel": true, "self": 88.69455132698181, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0021149570000034146, "count": 1, "is_parallel": true, "self": 0.0006439150001824601, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014710419998209545, "count": 8, "is_parallel": true, "self": 0.0014710419998209545 } } }, "UnityEnvironment.step": { "total": 0.05100207800001044, "count": 1, "is_parallel": true, "self": 0.0006920559997070086, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004520470001807553, "count": 1, "is_parallel": true, "self": 0.0004520470001807553 }, "communicator.exchange": { "total": 0.047934762000068076, "count": 1, "is_parallel": true, "self": 0.047934762000068076 }, "steps_from_proto": { "total": 0.0019232130000546022, "count": 1, "is_parallel": true, "self": 0.0004485859994929342, "children": { "_process_rank_one_or_two_observation": { "total": 0.001474627000561668, "count": 8, "is_parallel": true, "self": 0.001474627000561668 } } } } } } }, "UnityEnvironment.step": { "total": 101.21283997500632, "count": 6260, "is_parallel": true, "self": 3.3138291590228164, "children": { "UnityEnvironment._generate_step_input": { "total": 2.311905485000352, "count": 6260, "is_parallel": true, "self": 2.311905485000352 }, "communicator.exchange": { "total": 86.07016623400318, "count": 6260, "is_parallel": true, "self": 86.07016623400318 }, "steps_from_proto": { "total": 9.516939096979968, "count": 6260, "is_parallel": true, "self": 1.8333275359584604, "children": { "_process_rank_one_or_two_observation": { "total": 7.683611561021507, "count": 50080, "is_parallel": true, "self": 7.683611561021507 } } } } } } } } } } }, "trainer_advance": { "total": 63.43673607999153, "count": 6261, "self": 0.15980546998775935, "children": { "process_trajectory": { "total": 12.264903232003007, "count": 6261, "self": 12.264903232003007 }, "_update_policy": { "total": 51.01202737800077, "count": 32, "self": 29.677824931996838, "children": { "TorchPPOOptimizer.update": { "total": 21.33420244600393, "count": 2274, "self": 21.33420244600393 } } } } } } }, "trainer_threads": { "total": 9.469999895372894e-07, "count": 1, "self": 9.469999895372894e-07 }, "TrainerController._save_models": { "total": 0.11153023199995005, "count": 1, "self": 0.001507479999872885, "children": { "RLTrainer._checkpoint": { "total": 0.11002275200007716, "count": 1, "self": 0.11002275200007716 } } } } } } }