{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4670580327510834, "min": 0.45264092087745667, "max": 1.4188990592956543, "count": 37 }, "Pyramids.Policy.Entropy.sum": { "value": 13802.4990234375, "min": 13499.5625, "max": 43043.72265625, "count": 37 }, "Pyramids.Step.mean": { "value": 1109974.0, "min": 29952.0, "max": 1109974.0, "count": 37 }, "Pyramids.Step.sum": { "value": 1109974.0, "min": 29952.0, "max": 1109974.0, "count": 37 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5341798067092896, "min": -0.09405766427516937, "max": 0.6807253956794739, "count": 37 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 150.63870239257812, "min": -22.57383918762207, "max": 191.96456909179688, "count": 37 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.01106752548366785, "min": -0.00800732709467411, "max": 0.2739376723766327, "count": 37 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.121042251586914, "min": -2.0018317699432373, "max": 66.01898193359375, "count": 37 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06925084900729886, "min": 0.0653517246648248, "max": 0.07486915332026249, "count": 37 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.969511886102184, "min": 0.5240840732418375, "max": 1.070448996896933, "count": 37 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016656160964306894, "min": 0.0005057733982425383, "max": 0.017818263624775215, "count": 37 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.23318625350029654, "min": 0.0065750541771529974, "max": 0.249455690746853, "count": 37 }, "Pyramids.Policy.LearningRate.mean": { "value": 0.00019046913651030002, "min": 0.00019046913651030002, "max": 0.00029838354339596195, "count": 37 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0026665679111442003, "min": 0.0020886848037717336, "max": 0.0040112143629285665, "count": 37 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1634897, "min": 0.1634897, "max": 0.19946118095238097, "count": 37 }, "Pyramids.Policy.Epsilon.sum": { "value": 2.2888558, "min": 1.3962282666666668, "max": 2.782493166666667, "count": 37 }, "Pyramids.Policy.Beta.mean": { "value": 0.00635262103, "min": 0.00635262103, "max": 0.009946171977142856, "count": 37 }, "Pyramids.Policy.Beta.sum": { "value": 0.08893669442, "min": 0.06962320384, "max": 0.13371343619, "count": 37 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.007064522244036198, "min": 0.007064522244036198, "max": 0.34233716130256653, "count": 37 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.09890331327915192, "min": 0.09890331327915192, "max": 2.396360158920288, "count": 37 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 344.4891304347826, "min": 279.0103092783505, "max": 999.0, "count": 37 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31693.0, "min": 15984.0, "max": 33459.0, "count": 37 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5685282362544017, "min": -1.0000000521540642, "max": 1.6939519014782631, "count": 37 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 144.30459773540497, "min": -29.695801585912704, "max": 176.17099775373936, "count": 37 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5685282362544017, "min": -1.0000000521540642, "max": 1.6939519014782631, "count": 37 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 144.30459773540497, "min": -29.695801585912704, "max": 176.17099775373936, "count": 37 }, "Pyramids.Policy.RndReward.mean": { "value": 0.02536178988441901, "min": 0.02417710587809173, "max": 7.134387841448188, "count": 37 }, "Pyramids.Policy.RndReward.sum": { "value": 2.3332846693665488, "min": 2.1452003765152767, "max": 114.150205463171, "count": 37 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 37 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 37 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1713815528", "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": "1713818068" }, "total": 2540.279279016, "count": 1, "self": 0.3358441400009724, "children": { "run_training.setup": { "total": 0.04941984799961574, "count": 1, "self": 0.04941984799961574 }, "TrainerController.start_learning": { "total": 2539.8940150279996, "count": 1, "self": 1.514311556946268, "children": { "TrainerController._reset_env": { "total": 2.045940173999952, "count": 1, "self": 2.045940173999952 }, "TrainerController.advance": { "total": 2536.1961066680533, "count": 73020, "self": 1.559482338120688, "children": { "env_step": { "total": 1833.426749731052, "count": 73020, "self": 1684.1337375551361, "children": { "SubprocessEnvManager._take_step": { "total": 148.3437411669379, "count": 73020, "self": 5.341974778855729, "children": { "TorchPolicy.evaluate": { "total": 143.00176638808216, "count": 71254, "self": 143.00176638808216 } } }, "workers": { "total": 0.9492710089780303, "count": 73019, "self": 0.0, "children": { "worker_root": { "total": 2534.3053071040445, "count": 73019, "is_parallel": true, "self": 988.0212847669654, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0022215429999050684, "count": 1, "is_parallel": true, "self": 0.0006241659998522664, "children": { "_process_rank_one_or_two_observation": { "total": 0.001597377000052802, "count": 8, "is_parallel": true, "self": 0.001597377000052802 } } }, "UnityEnvironment.step": { "total": 0.1063030649997927, "count": 1, "is_parallel": true, "self": 0.0006769949995941715, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004686910001510114, "count": 1, "is_parallel": true, "self": 0.0004686910001510114 }, "communicator.exchange": { "total": 0.10339516400017601, "count": 1, "is_parallel": true, "self": 0.10339516400017601 }, "steps_from_proto": { "total": 0.001762214999871503, "count": 1, "is_parallel": true, "self": 0.0003690199996526644, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013931950002188387, "count": 8, "is_parallel": true, "self": 0.0013931950002188387 } } } } } } }, "UnityEnvironment.step": { "total": 1546.284022337079, "count": 73018, "is_parallel": true, "self": 38.74447715425822, "children": { "UnityEnvironment._generate_step_input": { "total": 28.021743310839156, "count": 73018, "is_parallel": true, "self": 28.021743310839156 }, "communicator.exchange": { "total": 1364.036709701958, "count": 73018, "is_parallel": true, "self": 1364.036709701958 }, "steps_from_proto": { "total": 115.48109217002366, "count": 73018, "is_parallel": true, "self": 23.481845745914598, "children": { "_process_rank_one_or_two_observation": { "total": 91.99924642410906, "count": 584144, "is_parallel": true, "self": 91.99924642410906 } } } } } } } } } } }, "trainer_advance": { "total": 701.2098745988806, "count": 73019, "self": 2.992946587894494, "children": { "process_trajectory": { "total": 146.90922696998268, "count": 73019, "self": 146.70914211098307, "children": { "RLTrainer._checkpoint": { "total": 0.2000848589996167, "count": 2, "self": 0.2000848589996167 } } }, "_update_policy": { "total": 551.3077010410034, "count": 521, "self": 322.336246237066, "children": { "TorchPPOOptimizer.update": { "total": 228.97145480393738, "count": 26004, "self": 228.97145480393738 } } } } } } }, "trainer_threads": { "total": 1.606000296305865e-06, "count": 1, "self": 1.606000296305865e-06 }, "TrainerController._save_models": { "total": 0.13765502299975196, "count": 1, "self": 0.0019576659997255774, "children": { "RLTrainer._checkpoint": { "total": 0.1356973570000264, "count": 1, "self": 0.1356973570000264 } } } } } } }