{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.6657443642616272, "min": 0.6547515392303467, "max": 1.4963154792785645, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 19993.634765625, "min": 19569.21484375, "max": 45392.2265625, "count": 33 }, "Pyramids.Step.mean": { "value": 989963.0, "min": 29952.0, "max": 989963.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989963.0, "min": 29952.0, "max": 989963.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.20976416766643524, "min": -0.17195451259613037, "max": 0.2098090648651123, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 52.86056900024414, "min": -40.75321960449219, "max": 53.71112060546875, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.5167282819747925, "min": -0.016544485464692116, "max": 0.5167282819747925, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 130.2155303955078, "min": -4.202299118041992, "max": 130.2155303955078, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06863616181653924, "min": 0.06433291350523164, "max": 0.07329156495630407, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0295424272480886, "min": 0.49466806910239597, "max": 1.0295424272480886, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.09128784775643403, "min": 4.6882479617894346e-05, "max": 0.09128784775643403, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 1.3693177163465104, "min": 0.0006094722350326265, "max": 1.3693177163465104, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.547477484206666e-06, "min": 7.547477484206666e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001132121622631, "min": 0.0001132121622631, "max": 0.0036341758886081, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10251579333333334, "min": 0.10251579333333334, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5377369, "min": 1.3886848, "max": 2.6113919, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002613277540000001, "min": 0.0002613277540000001, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003919916310000001, "min": 0.003919916310000001, "max": 0.12115805081, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009786485694348812, "min": 0.009786485694348812, "max": 0.4363475441932678, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1467972844839096, "min": 0.13966906070709229, "max": 3.0544328689575195, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 577.2916666666666, "min": 577.2916666666666, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 27710.0, "min": 15984.0, "max": 33140.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.9642458117256562, "min": -1.0000000521540642, "max": 0.9642458117256562, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 46.2837989628315, "min": -30.99320162832737, "max": 46.2837989628315, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.9642458117256562, "min": -1.0000000521540642, "max": 0.9642458117256562, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 46.2837989628315, "min": -30.99320162832737, "max": 46.2837989628315, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.05953307497232648, "min": 0.05953307497232648, "max": 8.708905439823866, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.857587598671671, "min": 2.857587598671671, "max": 139.34248703718185, "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": "1790114721", "python_version": "3.10.21 (main, Aug 13 2026, 09:45:30) [GCC 13.3.0]", "command_line_arguments": "/content/venv310/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=PyramidsTraining --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": "1790117044" }, "total": 2323.0919968320004, "count": 1, "self": 0.7860428240010151, "children": { "run_training.setup": { "total": 0.020731417999741097, "count": 1, "self": 0.020731417999741097 }, "TrainerController.start_learning": { "total": 2322.2852225899996, "count": 1, "self": 1.4877431378863548, "children": { "TrainerController._reset_env": { "total": 2.4716416609999214, "count": 1, "self": 2.4716416609999214 }, "TrainerController.advance": { "total": 2318.2099789231133, "count": 63305, "self": 1.4351058161446417, "children": { "env_step": { "total": 1677.0134691909716, "count": 63305, "self": 1520.4453060290307, "children": { "SubprocessEnvManager._take_step": { "total": 155.71852586495243, "count": 63305, "self": 4.696288594919679, "children": { "TorchPolicy.evaluate": { "total": 151.02223727003275, "count": 62561, "self": 151.02223727003275 } } }, "workers": { "total": 0.849637296988476, "count": 63305, "self": 0.0, "children": { "worker_root": { "total": 2316.1078035279834, "count": 63305, "is_parallel": true, "self": 916.0966878527579, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018537899995862972, "count": 1, "is_parallel": true, "self": 0.0006069069986551767, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012468830009311205, "count": 8, "is_parallel": true, "self": 0.0012468830009311205 } } }, "UnityEnvironment.step": { "total": 0.06300938399999723, "count": 1, "is_parallel": true, "self": 0.0017540349990667892, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00046457000007649185, "count": 1, "is_parallel": true, "self": 0.00046457000007649185 }, "communicator.exchange": { "total": 0.05601578500045434, "count": 1, "is_parallel": true, "self": 0.05601578500045434 }, "steps_from_proto": { "total": 0.004774994000399602, "count": 1, "is_parallel": true, "self": 0.00045121600032871356, "children": { "_process_rank_one_or_two_observation": { "total": 0.004323778000070888, "count": 8, "is_parallel": true, "self": 0.004323778000070888 } } } } } } }, "UnityEnvironment.step": { "total": 1400.0111156752255, "count": 63304, "is_parallel": true, "self": 33.755694798348486, "children": { "UnityEnvironment._generate_step_input": { "total": 22.4577600240209, "count": 63304, "is_parallel": true, "self": 22.4577600240209 }, "communicator.exchange": { "total": 1232.8168996469012, "count": 63304, "is_parallel": true, "self": 1232.8168996469012 }, "steps_from_proto": { "total": 110.98076120595488, "count": 63304, "is_parallel": true, "self": 23.193871279838277, "children": { "_process_rank_one_or_two_observation": { "total": 87.7868899261166, "count": 506432, "is_parallel": true, "self": 87.7868899261166 } } } } } } } } } } }, "trainer_advance": { "total": 639.7614039159971, "count": 63305, "self": 2.7616113909080013, "children": { "process_trajectory": { "total": 113.55976351210666, "count": 63305, "self": 113.26664491810698, "children": { "RLTrainer._checkpoint": { "total": 0.29311859399967943, "count": 2, "self": 0.29311859399967943 } } }, "_update_policy": { "total": 523.4400290129824, "count": 449, "self": 281.0773568820923, "children": { "TorchPPOOptimizer.update": { "total": 242.36267213089013, "count": 22770, "self": 242.36267213089013 } } } } } } }, "trainer_threads": { "total": 1.2729997251881287e-06, "count": 1, "self": 1.2729997251881287e-06 }, "TrainerController._save_models": { "total": 0.1158575950003069, "count": 1, "self": 0.0014822579996689456, "children": { "RLTrainer._checkpoint": { "total": 0.11437533700063796, "count": 1, "self": 0.11437533700063796 } } } } } } }