{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.48961931467056274, "min": 0.48961931467056274, "max": 1.4358364343643188, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 14563.2373046875, "min": 14563.2373046875, "max": 43557.53515625, "count": 33 }, "Pyramids.Step.mean": { "value": 989948.0, "min": 29952.0, "max": 989948.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989948.0, "min": 29952.0, "max": 989948.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5870927572250366, "min": -0.2063315063714981, "max": 0.5870927572250366, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 167.32144165039062, "min": -48.90056610107422, "max": 167.32144165039062, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.008662767708301544, "min": -0.014964998699724674, "max": 0.3496842384338379, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 2.468888759613037, "min": -4.010619640350342, "max": 82.87516784667969, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06889947521752524, "min": 0.0641984300288771, "max": 0.07278443145387598, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9645926530453532, "min": 0.501175922426949, "max": 1.0622457314651303, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015839299129202986, "min": 0.00010409314958800455, "max": 0.016233065845638824, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.22175018780884181, "min": 0.0014573040942320638, "max": 0.2434959876845824, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.294833282707137e-06, "min": 7.294833282707137e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010212766595789992, "min": 0.00010212766595789992, "max": 0.0033835286721572, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10243157857142858, "min": 0.10243157857142858, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4340421, "min": 1.3886848, "max": 2.5278428, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025291469928571416, "min": 0.00025291469928571416, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003540805789999998, "min": 0.003540805789999998, "max": 0.11281149572, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.008177466690540314, "min": 0.007845316082239151, "max": 0.3454439043998718, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.11448453366756439, "min": 0.11314088106155396, "max": 2.418107271194458, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 327.3478260869565, "min": 327.3478260869565, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30116.0, "min": 15984.0, "max": 32670.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6348461366289264, "min": -1.0000000521540642, "max": 1.6348461366289264, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 148.7709984332323, "min": -30.702001735568047, "max": 148.7709984332323, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6348461366289264, "min": -1.0000000521540642, "max": 1.6348461366289264, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 148.7709984332323, "min": -30.702001735568047, "max": 148.7709984332323, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.027118850615646967, "min": 0.027118850615646967, "max": 6.860795432701707, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.467815406023874, "min": 2.451593256846536, "max": 109.77272692322731, "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": "1697621043", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "2.0.1+cu118", "numpy_version": "1.23.5", "end_time_seconds": "1697623284" }, "total": 2241.2717820939997, "count": 1, "self": 0.49286338799993246, "children": { "run_training.setup": { "total": 0.044765146000031564, "count": 1, "self": 0.044765146000031564 }, "TrainerController.start_learning": { "total": 2240.73415356, "count": 1, "self": 1.3346242050256478, "children": { "TrainerController._reset_env": { "total": 7.816889100000026, "count": 1, "self": 7.816889100000026 }, "TrainerController.advance": { "total": 2231.503753694974, "count": 63662, "self": 1.4065277810577754, "children": { "env_step": { "total": 1589.14357397198, "count": 63662, "self": 1461.3013536309215, "children": { "SubprocessEnvManager._take_step": { "total": 127.02462406001672, "count": 63662, "self": 4.781223866998346, "children": { "TorchPolicy.evaluate": { "total": 122.24340019301837, "count": 62550, "self": 122.24340019301837 } } }, "workers": { "total": 0.8175962810418014, "count": 63662, "self": 0.0, "children": { "worker_root": { "total": 2236.180835088982, "count": 63662, "is_parallel": true, "self": 892.7924007289744, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0056347060000234706, "count": 1, "is_parallel": true, "self": 0.003654760000188162, "children": { "_process_rank_one_or_two_observation": { "total": 0.0019799459998353086, "count": 8, "is_parallel": true, "self": 0.0019799459998353086 } } }, "UnityEnvironment.step": { "total": 0.04897819400002845, "count": 1, "is_parallel": true, "self": 0.000599248000071384, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005139749999898413, "count": 1, "is_parallel": true, "self": 0.0005139749999898413 }, "communicator.exchange": { "total": 0.04623507599995946, "count": 1, "is_parallel": true, "self": 0.04623507599995946 }, "steps_from_proto": { "total": 0.0016298950000077639, "count": 1, "is_parallel": true, "self": 0.0003750179999997272, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012548770000080367, "count": 8, "is_parallel": true, "self": 0.0012548770000080367 } } } } } } }, "UnityEnvironment.step": { "total": 1343.3884343600075, "count": 63661, "is_parallel": true, "self": 35.61511579707894, "children": { "UnityEnvironment._generate_step_input": { "total": 24.745647940959145, "count": 63661, "is_parallel": true, "self": 24.745647940959145 }, "communicator.exchange": { "total": 1182.6201432669945, "count": 63661, "is_parallel": true, "self": 1182.6201432669945 }, "steps_from_proto": { "total": 100.40752735497495, "count": 63661, "is_parallel": true, "self": 19.987222054121787, "children": { "_process_rank_one_or_two_observation": { "total": 80.42030530085316, "count": 509288, "is_parallel": true, "self": 80.42030530085316 } } } } } } } } } } }, "trainer_advance": { "total": 640.9536519419362, "count": 63662, "self": 2.48728760294739, "children": { "process_trajectory": { "total": 122.06907820598923, "count": 63662, "self": 121.79706501498919, "children": { "RLTrainer._checkpoint": { "total": 0.27201319100004184, "count": 2, "self": 0.27201319100004184 } } }, "_update_policy": { "total": 516.3972861329996, "count": 446, "self": 309.7660623019841, "children": { "TorchPPOOptimizer.update": { "total": 206.63122383101552, "count": 22857, "self": 206.63122383101552 } } } } } } }, "trainer_threads": { "total": 1.1239999366807751e-06, "count": 1, "self": 1.1239999366807751e-06 }, "TrainerController._save_models": { "total": 0.07888543600029152, "count": 1, "self": 0.0015133340002648765, "children": { "RLTrainer._checkpoint": { "total": 0.07737210200002664, "count": 1, "self": 0.07737210200002664 } } } } } } }