{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.30621960759162903, "min": 0.29827240109443665, "max": 1.4267065525054932, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 9264.98046875, "min": 8876.5869140625, "max": 43280.5703125, "count": 33 }, "Pyramids.Step.mean": { "value": 989972.0, "min": 29887.0, "max": 989972.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989972.0, "min": 29887.0, "max": 989972.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6472200155258179, "min": -0.0905347466468811, "max": 0.6472200155258179, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 183.81048583984375, "min": -21.909408569335938, "max": 183.81048583984375, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.03800541162490845, "min": -0.010601380839943886, "max": 0.36488187313079834, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 10.793537139892578, "min": -2.9502577781677246, "max": 86.84188842773438, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07136590786503089, "min": 0.0653866980900024, "max": 0.07362963908818435, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9991227101104324, "min": 0.6453146300881387, "max": 1.0494529856157753, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014343336989244847, "min": 0.0013855546718551431, "max": 0.01650544545208547, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.20080671784942786, "min": 0.019397765405972003, "max": 0.2310762363291966, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.726340281728571e-06, "min": 7.726340281728571e-06, "max": 0.0002948055350648222, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010816876394419999, "min": 0.00010816876394419999, "max": 0.0037591192469602994, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10257541428571429, "min": 0.10257541428571429, "max": 0.1982685111111111, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4360558, "min": 1.4360558, "max": 2.6530397000000003, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026728388714285716, "min": 0.00026728388714285716, "max": 0.009827024260000001, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.00374197442, "min": 0.00374197442, "max": 0.12531866603, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.011572890914976597, "min": 0.011572890914976597, "max": 0.5379387736320496, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1620204746723175, "min": 0.1620204746723175, "max": 4.841448783874512, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 310.10526315789474, "min": 284.56880733944956, "max": 982.15625, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29460.0, "min": 16813.0, "max": 32378.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6267136612220814, "min": -0.795531301992014, "max": 1.6601872551170263, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 154.53779781609774, "min": -25.7330015078187, "max": 182.6205980628729, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6267136612220814, "min": -0.795531301992014, "max": 1.6601872551170263, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 154.53779781609774, "min": -25.7330015078187, "max": 182.6205980628729, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03730413428642542, "min": 0.03730413428642542, "max": 10.78130971122947, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.543892757210415, "min": 3.543892757210415, "max": 194.06357480213046, "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": "1688564129", "python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [GCC 9.4.0]", "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": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1688567444" }, "total": 3314.3982870930004, "count": 1, "self": 1.4141944199996033, "children": { "run_training.setup": { "total": 0.05799253600025622, "count": 1, "self": 0.05799253600025622 }, "TrainerController.start_learning": { "total": 3312.9261001370005, "count": 1, "self": 2.3243206050819936, "children": { "TrainerController._reset_env": { "total": 6.074027666000347, "count": 1, "self": 6.074027666000347 }, "TrainerController.advance": { "total": 3304.3734236019177, "count": 64150, "self": 2.210455799014653, "children": { "env_step": { "total": 2197.194663189974, "count": 64150, "self": 2019.8864446139628, "children": { "SubprocessEnvManager._take_step": { "total": 176.0208877739633, "count": 64150, "self": 7.327412672859737, "children": { "TorchPolicy.evaluate": { "total": 168.69347510110356, "count": 62548, "self": 168.69347510110356 } } }, "workers": { "total": 1.287330802048018, "count": 64150, "self": 0.0, "children": { "worker_root": { "total": 3307.2955606969645, "count": 64150, "is_parallel": true, "self": 1466.2979167289309, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0025221579999197274, "count": 1, "is_parallel": true, "self": 0.0007122139995772159, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018099440003425116, "count": 8, "is_parallel": true, "self": 0.0018099440003425116 } } }, "UnityEnvironment.step": { "total": 0.07621390100030112, "count": 1, "is_parallel": true, "self": 0.0005586599995694996, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004563300003610493, "count": 1, "is_parallel": true, "self": 0.0004563300003610493 }, "communicator.exchange": { "total": 0.07334933600031945, "count": 1, "is_parallel": true, "self": 0.07334933600031945 }, "steps_from_proto": { "total": 0.001849575000051118, "count": 1, "is_parallel": true, "self": 0.00035362799962967983, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014959470004214381, "count": 8, "is_parallel": true, "self": 0.0014959470004214381 } } } } } } }, "UnityEnvironment.step": { "total": 1840.9976439680336, "count": 64149, "is_parallel": true, "self": 36.71287367406967, "children": { "UnityEnvironment._generate_step_input": { "total": 22.487694091029425, "count": 64149, "is_parallel": true, "self": 22.487694091029425 }, "communicator.exchange": { "total": 1673.4045214330172, "count": 64149, "is_parallel": true, "self": 1673.4045214330172 }, "steps_from_proto": { "total": 108.3925547699173, "count": 64149, "is_parallel": true, "self": 21.170980506639808, "children": { "_process_rank_one_or_two_observation": { "total": 87.22157426327749, "count": 513192, "is_parallel": true, "self": 87.22157426327749 } } } } } } } } } } }, "trainer_advance": { "total": 1104.968304612929, "count": 64150, "self": 4.889250951964186, "children": { "process_trajectory": { "total": 185.8116197549698, "count": 64150, "self": 185.4987527359699, "children": { "RLTrainer._checkpoint": { "total": 0.31286701899989566, "count": 2, "self": 0.31286701899989566 } } }, "_update_policy": { "total": 914.267433905995, "count": 461, "self": 627.4323879520462, "children": { "TorchPPOOptimizer.update": { "total": 286.8350459539488, "count": 22779, "self": 286.8350459539488 } } } } } } }, "trainer_threads": { "total": 1.2700002116616815e-06, "count": 1, "self": 1.2700002116616815e-06 }, "TrainerController._save_models": { "total": 0.1543269940002574, "count": 1, "self": 0.0020192319998386665, "children": { "RLTrainer._checkpoint": { "total": 0.15230776200041873, "count": 1, "self": 0.15230776200041873 } } } } } } }