{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4080785810947418, "min": 0.4080785810947418, "max": 1.2320975065231323, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 12222.76953125, "min": 12222.76953125, "max": 37376.91015625, "count": 33 }, "Pyramids.Step.mean": { "value": 989978.0, "min": 29952.0, "max": 989978.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989978.0, "min": 29952.0, "max": 989978.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.7012405395507812, "min": -0.19191142916679382, "max": 0.7012405395507812, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 190.0361785888672, "min": -46.25065612792969, "max": 190.0361785888672, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.201072558760643, "min": -0.05749780312180519, "max": 0.4325537383556366, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 54.49066162109375, "min": -14.834433555603027, "max": 102.5152359008789, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06627741552143736, "min": 0.0650135630111377, "max": 0.07875053462263103, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.927883817300123, "min": 0.5512537423584172, "max": 1.0543325000908226, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014260766986851756, "min": 0.0006256178160617287, "max": 0.020137641515161488, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.19965073781592457, "min": 0.008133031608802473, "max": 0.28192698121226084, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.59948318115714e-06, "min": 7.59948318115714e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010639276453619997, "min": 0.00010639276453619997, "max": 0.0035081387306205004, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10506625714285715, "min": 0.10506625714285715, "max": 0.2967670857142858, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4709276000000002, "min": 1.4709276000000002, "max": 3.7387589999999995, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026305954428571427, "min": 0.00026305954428571427, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036828336199999996, "min": 0.0036828336199999996, "max": 0.11696101205, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010993401519954205, "min": 0.010993401519954205, "max": 0.463376522064209, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1539076268672943, "min": 0.1539076268672943, "max": 3.243635654449463, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 387.8082191780822, "min": 377.2345679012346, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28310.0, "min": 15984.0, "max": 34310.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.475175324878464, "min": -1.0000000521540642, "max": 1.4992715818462548, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 107.68779871612787, "min": -29.934601679444313, "max": 121.44099812954664, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.475175324878464, "min": -1.0000000521540642, "max": 1.4992715818462548, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 107.68779871612787, "min": -29.934601679444313, "max": 121.44099812954664, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.044458862496555895, "min": 0.044458862496555895, "max": 9.41978757083416, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.2454969622485805, "min": 3.2454969622485805, "max": 150.71660113334656, "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": "1700224280", "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": "2.1.0+cu118", "numpy_version": "1.23.5", "end_time_seconds": "1700226501" }, "total": 2221.3547279859995, "count": 1, "self": 0.4754672979993302, "children": { "run_training.setup": { "total": 0.04142081000009057, "count": 1, "self": 0.04142081000009057 }, "TrainerController.start_learning": { "total": 2220.837839878, "count": 1, "self": 1.38578868796003, "children": { "TrainerController._reset_env": { "total": 3.3689679430001434, "count": 1, "self": 3.3689679430001434 }, "TrainerController.advance": { "total": 2216.000478661041, "count": 63577, "self": 1.4560039290408895, "children": { "env_step": { "total": 1581.4895533920323, "count": 63577, "self": 1448.03114958308, "children": { "SubprocessEnvManager._take_step": { "total": 132.60081954796715, "count": 63577, "self": 4.59733608792385, "children": { "TorchPolicy.evaluate": { "total": 128.0034834600433, "count": 62549, "self": 128.0034834600433 } } }, "workers": { "total": 0.8575842609852771, "count": 63577, "self": 0.0, "children": { "worker_root": { "total": 2216.0080060800124, "count": 63577, "is_parallel": true, "self": 891.4087300660201, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018634230000316165, "count": 1, "is_parallel": true, "self": 0.000591125000255488, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012722979997761286, "count": 8, "is_parallel": true, "self": 0.0012722979997761286 } } }, "UnityEnvironment.step": { "total": 0.045073990999981106, "count": 1, "is_parallel": true, "self": 0.0005590480000137177, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00047381900003529154, "count": 1, "is_parallel": true, "self": 0.00047381900003529154 }, "communicator.exchange": { "total": 0.04230647099984708, "count": 1, "is_parallel": true, "self": 0.04230647099984708 }, "steps_from_proto": { "total": 0.001734653000085018, "count": 1, "is_parallel": true, "self": 0.0003675709999697574, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013670820001152606, "count": 8, "is_parallel": true, "self": 0.0013670820001152606 } } } } } } }, "UnityEnvironment.step": { "total": 1324.5992760139923, "count": 63576, "is_parallel": true, "self": 34.63257074698254, "children": { "UnityEnvironment._generate_step_input": { "total": 25.324120327986975, "count": 63576, "is_parallel": true, "self": 25.324120327986975 }, "communicator.exchange": { "total": 1162.7083945480326, "count": 63576, "is_parallel": true, "self": 1162.7083945480326 }, "steps_from_proto": { "total": 101.93419039099012, "count": 63576, "is_parallel": true, "self": 20.4955127049966, "children": { "_process_rank_one_or_two_observation": { "total": 81.43867768599353, "count": 508608, "is_parallel": true, "self": 81.43867768599353 } } } } } } } } } } }, "trainer_advance": { "total": 633.0549213399679, "count": 63577, "self": 2.5803982169070423, "children": { "process_trajectory": { "total": 126.01360010105577, "count": 63577, "self": 125.84986732805487, "children": { "RLTrainer._checkpoint": { "total": 0.16373277300090194, "count": 2, "self": 0.16373277300090194 } } }, "_update_policy": { "total": 504.4609230220051, "count": 448, "self": 301.98452709802064, "children": { "TorchPPOOptimizer.update": { "total": 202.47639592398446, "count": 22791, "self": 202.47639592398446 } } } } } } }, "trainer_threads": { "total": 8.929991963668726e-07, "count": 1, "self": 8.929991963668726e-07 }, "TrainerController._save_models": { "total": 0.0826036929993279, "count": 1, "self": 0.001286749999053427, "children": { "RLTrainer._checkpoint": { "total": 0.08131694300027448, "count": 1, "self": 0.08131694300027448 } } } } } } }