{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.24776344001293182, "min": 0.23747022449970245, "max": 1.4693641662597656, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 7444.7958984375, "min": 7173.50048828125, "max": 44574.6328125, "count": 33 }, "Pyramids.Step.mean": { "value": 989984.0, "min": 29952.0, "max": 989984.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989984.0, "min": 29952.0, "max": 989984.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5388349294662476, "min": -0.0943683311343193, "max": 0.6009039878845215, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 150.873779296875, "min": -22.837135314941406, "max": 169.92530822753906, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.0019570179283618927, "min": -0.0019570179283618927, "max": 0.604152262210846, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -0.5479650497436523, "min": -0.5479650497436523, "max": 143.18408203125, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06723217216922957, "min": 0.06525790482142019, "max": 0.07538219869061494, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0084825825384436, "min": 0.48104145756575417, "max": 1.0840813761055423, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015522339491130252, "min": 0.0002178835768923369, "max": 0.018705674545090784, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2328350923669538, "min": 0.002178835768923369, "max": 0.24494778489558186, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.493997502033332e-06, "min": 7.493997502033332e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011240996253049998, "min": 0.00011240996253049998, "max": 0.0032555667148112, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10249796666666669, "min": 0.10249796666666669, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5374695000000003, "min": 1.3691136000000002, "max": 2.4851888000000004, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025954687000000003, "min": 0.00025954687000000003, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0038932030500000007, "min": 0.0038932030500000007, "max": 0.10855036112000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.011122395284473896, "min": 0.011122395284473896, "max": 0.62539142370224, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1668359339237213, "min": 0.15988396108150482, "max": 4.377739906311035, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 350.81481481481484, "min": 326.0674157303371, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28416.0, "min": 15984.0, "max": 32493.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6244814632299505, "min": -1.0000000521540642, "max": 1.6525733179516262, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 131.582998521626, "min": -32.000001668930054, "max": 150.1709986254573, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6244814632299505, "min": -1.0000000521540642, "max": 1.6525733179516262, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 131.582998521626, "min": -32.000001668930054, "max": 150.1709986254573, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03997597598936409, "min": 0.03993689334550923, "max": 14.091310841962695, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.238054055138491, "min": 3.238054055138491, "max": 225.46097347140312, "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": "1707424667", "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": "2.2.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1707426890" }, "total": 2222.488577445, "count": 1, "self": 0.4767212489996382, "children": { "run_training.setup": { "total": 0.05198154700019586, "count": 1, "self": 0.05198154700019586 }, "TrainerController.start_learning": { "total": 2221.959874649, "count": 1, "self": 1.4201043830016715, "children": { "TrainerController._reset_env": { "total": 2.4473638730000857, "count": 1, "self": 2.4473638730000857 }, "TrainerController.advance": { "total": 2218.002140349998, "count": 64036, "self": 1.4685293710531369, "children": { "env_step": { "total": 1596.4707010460136, "count": 64036, "self": 1465.46610076803, "children": { "SubprocessEnvManager._take_step": { "total": 130.12977718999878, "count": 64036, "self": 4.639282245927916, "children": { "TorchPolicy.evaluate": { "total": 125.49049494407086, "count": 62570, "self": 125.49049494407086 } } }, "workers": { "total": 0.8748230879848506, "count": 64036, "self": 0.0, "children": { "worker_root": { "total": 2216.758486618993, "count": 64036, "is_parallel": true, "self": 865.8537772339541, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0020991979999962496, "count": 1, "is_parallel": true, "self": 0.0007315949997064308, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013676030002898187, "count": 8, "is_parallel": true, "self": 0.0013676030002898187 } } }, "UnityEnvironment.step": { "total": 0.05543698799988306, "count": 1, "is_parallel": true, "self": 0.0005936210000072606, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004630079999969894, "count": 1, "is_parallel": true, "self": 0.0004630079999969894 }, "communicator.exchange": { "total": 0.05252296200001183, "count": 1, "is_parallel": true, "self": 0.05252296200001183 }, "steps_from_proto": { "total": 0.0018573969998669781, "count": 1, "is_parallel": true, "self": 0.0003565819995401398, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015008150003268383, "count": 8, "is_parallel": true, "self": 0.0015008150003268383 } } } } } } }, "UnityEnvironment.step": { "total": 1350.904709385039, "count": 64035, "is_parallel": true, "self": 34.95263637706785, "children": { "UnityEnvironment._generate_step_input": { "total": 23.84083730599491, "count": 64035, "is_parallel": true, "self": 23.84083730599491 }, "communicator.exchange": { "total": 1193.7673012219507, "count": 64035, "is_parallel": true, "self": 1193.7673012219507 }, "steps_from_proto": { "total": 98.34393448002561, "count": 64035, "is_parallel": true, "self": 19.533894922818945, "children": { "_process_rank_one_or_two_observation": { "total": 78.81003955720666, "count": 512280, "is_parallel": true, "self": 78.81003955720666 } } } } } } } } } } }, "trainer_advance": { "total": 620.0629099329315, "count": 64036, "self": 2.810763528950474, "children": { "process_trajectory": { "total": 124.65588369398233, "count": 64036, "self": 124.42313210498219, "children": { "RLTrainer._checkpoint": { "total": 0.23275158900014503, "count": 2, "self": 0.23275158900014503 } } }, "_update_policy": { "total": 492.59626270999865, "count": 438, "self": 289.7020671590092, "children": { "TorchPPOOptimizer.update": { "total": 202.89419555098948, "count": 22833, "self": 202.89419555098948 } } } } } } }, "trainer_threads": { "total": 1.3180001587898005e-06, "count": 1, "self": 1.3180001587898005e-06 }, "TrainerController._save_models": { "total": 0.09026472499999727, "count": 1, "self": 0.0016265820004264242, "children": { "RLTrainer._checkpoint": { "total": 0.08863814299957085, "count": 1, "self": 0.08863814299957085 } } } } } } }