{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4496605098247528, "min": 0.44725897908210754, "max": 1.4203987121582031, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 13425.064453125, "min": 13425.064453125, "max": 43089.21484375, "count": 33 }, "Pyramids.Step.mean": { "value": 989950.0, "min": 29952.0, "max": 989950.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989950.0, "min": 29952.0, "max": 989950.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.4410683214664459, "min": -0.09438677132129669, "max": 0.44679006934165955, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 117.32417297363281, "min": -22.747211456298828, "max": 118.39936828613281, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.02166244015097618, "min": 0.004690803121775389, "max": 0.3096609115600586, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 5.762208938598633, "min": 1.257135272026062, "max": 74.62828063964844, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06712939155404456, "min": 0.06310612193614645, "max": 0.07426697016120751, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0069408733106684, "min": 0.5198687911284525, "max": 1.06502585002454, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014275552474686669, "min": 9.64751464294081e-05, "max": 0.015094648061551875, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21413328712030003, "min": 0.0012541769035823052, "max": 0.22641972092327814, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.5295974901666655e-06, "min": 7.5295974901666655e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011294396235249998, "min": 0.00011294396235249998, "max": 0.0036347959884013995, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10250983333333334, "min": 0.10250983333333334, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5376475, "min": 1.3886848, "max": 2.6175044, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026073234999999997, "min": 0.00026073234999999997, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0039109852499999995, "min": 0.0039109852499999995, "max": 0.12117870013999998, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009830583818256855, "min": 0.009830583818256855, "max": 0.6006709933280945, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1474587619304657, "min": 0.1401887834072113, "max": 4.204697132110596, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 425.4428571428571, "min": 401.7260273972603, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29781.0, "min": 15984.0, "max": 32503.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.488811404790197, "min": -1.0000000521540642, "max": 1.488811404790197, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 104.2167983353138, "min": -31.989601641893387, "max": 108.28219812363386, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.488811404790197, "min": -1.0000000521540642, "max": 1.488811404790197, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 104.2167983353138, "min": -31.989601641893387, "max": 108.28219812363386, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04392006372800097, "min": 0.04392006372800097, "max": 12.819432344287634, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.074404460960068, "min": 3.02317702419532, "max": 205.11091750860214, "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": "1748853013", "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": "2.7.0+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1748855301" }, "total": 2287.66375926, "count": 1, "self": 0.5262872150001385, "children": { "run_training.setup": { "total": 0.020351246000245737, "count": 1, "self": 0.020351246000245737 }, "TrainerController.start_learning": { "total": 2287.1171207989996, "count": 1, "self": 1.2866967519598802, "children": { "TrainerController._reset_env": { "total": 2.8552870749999784, "count": 1, "self": 2.8552870749999784 }, "TrainerController.advance": { "total": 2282.889447572039, "count": 63695, "self": 1.348595003979426, "children": { "env_step": { "total": 1605.8923090979565, "count": 63695, "self": 1455.5528562839627, "children": { "SubprocessEnvManager._take_step": { "total": 149.5763137209583, "count": 63695, "self": 4.602102556985756, "children": { "TorchPolicy.evaluate": { "total": 144.97421116397254, "count": 62568, "self": 144.97421116397254 } } }, "workers": { "total": 0.7631390930355337, "count": 63695, "self": 0.0, "children": { "worker_root": { "total": 2282.079897979919, "count": 63695, "is_parallel": true, "self": 938.1965698530444, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0021469180001076893, "count": 1, "is_parallel": true, "self": 0.0006848070006526541, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014621109994550352, "count": 8, "is_parallel": true, "self": 0.0014621109994550352 } } }, "UnityEnvironment.step": { "total": 0.07653444900006434, "count": 1, "is_parallel": true, "self": 0.0005186480002521421, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004286069997760933, "count": 1, "is_parallel": true, "self": 0.0004286069997760933 }, "communicator.exchange": { "total": 0.07394713700023203, "count": 1, "is_parallel": true, "self": 0.07394713700023203 }, "steps_from_proto": { "total": 0.0016400569998040737, "count": 1, "is_parallel": true, "self": 0.00033048399973267806, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013095730000713957, "count": 8, "is_parallel": true, "self": 0.0013095730000713957 } } } } } } }, "UnityEnvironment.step": { "total": 1343.8833281268749, "count": 63694, "is_parallel": true, "self": 31.657103102872497, "children": { "UnityEnvironment._generate_step_input": { "total": 23.669921956041435, "count": 63694, "is_parallel": true, "self": 23.669921956041435 }, "communicator.exchange": { "total": 1191.9187643819187, "count": 63694, "is_parallel": true, "self": 1191.9187643819187 }, "steps_from_proto": { "total": 96.63753868604226, "count": 63694, "is_parallel": true, "self": 19.133771818095283, "children": { "_process_rank_one_or_two_observation": { "total": 77.50376686794698, "count": 509552, "is_parallel": true, "self": 77.50376686794698 } } } } } } } } } } }, "trainer_advance": { "total": 675.648543470103, "count": 63695, "self": 2.5957560410602127, "children": { "process_trajectory": { "total": 130.0042602910471, "count": 63695, "self": 129.74787680504733, "children": { "RLTrainer._checkpoint": { "total": 0.2563834859997769, "count": 2, "self": 0.2563834859997769 } } }, "_update_policy": { "total": 543.0485271379957, "count": 455, "self": 305.3452910630117, "children": { "TorchPPOOptimizer.update": { "total": 237.70323607498403, "count": 22767, "self": 237.70323607498403 } } } } } } }, "trainer_threads": { "total": 8.940005500335246e-07, "count": 1, "self": 8.940005500335246e-07 }, "TrainerController._save_models": { "total": 0.08568850600022415, "count": 1, "self": 0.0014467900000454392, "children": { "RLTrainer._checkpoint": { "total": 0.08424171600017871, "count": 1, "self": 0.08424171600017871 } } } } } } }