{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.8369749188423157, "min": 0.8090046644210815, "max": 1.4497430324554443, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 25470.8203125, "min": 24231.30859375, "max": 43979.40625, "count": 33 }, "Pyramids.Step.mean": { "value": 989990.0, "min": 29952.0, "max": 989990.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989990.0, "min": 29952.0, "max": 989990.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.2350318729877472, "min": -0.11264254152774811, "max": 0.2464633584022522, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 59.933128356933594, "min": -27.25949478149414, "max": 63.587547302246094, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.04709357023239136, "min": -0.0014552576467394829, "max": 0.3850932717323303, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 12.00886058807373, "min": -0.36526966094970703, "max": 91.26710510253906, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07090225976555505, "min": 0.06392303770518906, "max": 0.07303618280473968, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0635338964833256, "min": 0.4781546034587911, "max": 1.0635338964833256, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.011282450104004561, "min": 0.00013776707802311722, "max": 0.014766214985554272, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.16923675156006843, "min": 0.0019287390923236412, "max": 0.2067270097977598, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.440157519979997e-06, "min": 7.440157519979997e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011160236279969996, "min": 0.00011160236279969996, "max": 0.003508919630360199, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10248002000000002, "min": 0.10248002000000002, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5372003000000003, "min": 1.3886848, "max": 2.5696398000000005, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025775399799999986, "min": 0.00025775399799999986, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003866309969999998, "min": 0.003866309969999998, "max": 0.11698701602, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010654088109731674, "min": 0.010488994419574738, "max": 0.35650160908699036, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.15981131792068481, "min": 0.14684592187404633, "max": 2.495511293411255, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 572.469387755102, "min": 572.469387755102, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28051.0, "min": 15984.0, "max": 32739.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.1009183437848578, "min": -1.0000000521540642, "max": 1.1009183437848578, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 53.94499884545803, "min": -31.99440163373947, "max": 57.66659864783287, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.1009183437848578, "min": -1.0000000521540642, "max": 1.1009183437848578, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 53.94499884545803, "min": -31.99440163373947, "max": 57.66659864783287, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.06304745051572669, "min": 0.06304745051572669, "max": 7.048223110847175, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.089325075270608, "min": 3.089325075270608, "max": 112.7715697735548, "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": "1681395906", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[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": "1681397862" }, "total": 1955.6913732950002, "count": 1, "self": 0.43588859700003013, "children": { "run_training.setup": { "total": 0.11331390299983468, "count": 1, "self": 0.11331390299983468 }, "TrainerController.start_learning": { "total": 1955.1421707950003, "count": 1, "self": 1.3933385219957017, "children": { "TrainerController._reset_env": { "total": 4.01655364699991, "count": 1, "self": 4.01655364699991 }, "TrainerController.advance": { "total": 1949.6285327700052, "count": 63280, "self": 1.4412048679600957, "children": { "env_step": { "total": 1351.2243465010806, "count": 63280, "self": 1245.4393796631048, "children": { "SubprocessEnvManager._take_step": { "total": 104.97075020602324, "count": 63280, "self": 4.7408724349234035, "children": { "TorchPolicy.evaluate": { "total": 100.22987777109984, "count": 62561, "self": 100.22987777109984 } } }, "workers": { "total": 0.8142166319526041, "count": 63280, "self": 0.0, "children": { "worker_root": { "total": 1950.4691251900576, "count": 63280, "is_parallel": true, "self": 812.231106169088, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001752971999849251, "count": 1, "is_parallel": true, "self": 0.0005749389993070508, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011780330005422002, "count": 8, "is_parallel": true, "self": 0.0011780330005422002 } } }, "UnityEnvironment.step": { "total": 0.09923613900036798, "count": 1, "is_parallel": true, "self": 0.0005393370006459008, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004712869999821123, "count": 1, "is_parallel": true, "self": 0.0004712869999821123 }, "communicator.exchange": { "total": 0.09662423300005685, "count": 1, "is_parallel": true, "self": 0.09662423300005685 }, "steps_from_proto": { "total": 0.001601281999683124, "count": 1, "is_parallel": true, "self": 0.00044214599938641186, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011591360002967122, "count": 8, "is_parallel": true, "self": 0.0011591360002967122 } } } } } } }, "UnityEnvironment.step": { "total": 1138.2380190209697, "count": 63279, "is_parallel": true, "self": 31.67930967097709, "children": { "UnityEnvironment._generate_step_input": { "total": 23.33917068711844, "count": 63279, "is_parallel": true, "self": 23.33917068711844 }, "communicator.exchange": { "total": 989.5725778649025, "count": 63279, "is_parallel": true, "self": 989.5725778649025 }, "steps_from_proto": { "total": 93.64696079797159, "count": 63279, "is_parallel": true, "self": 20.1513044739404, "children": { "_process_rank_one_or_two_observation": { "total": 73.49565632403119, "count": 506232, "is_parallel": true, "self": 73.49565632403119 } } } } } } } } } } }, "trainer_advance": { "total": 596.9629814009645, "count": 63280, "self": 2.604591855862054, "children": { "process_trajectory": { "total": 103.71332395409945, "count": 63280, "self": 103.45949447109933, "children": { "RLTrainer._checkpoint": { "total": 0.25382948300011776, "count": 2, "self": 0.25382948300011776 } } }, "_update_policy": { "total": 490.645065591003, "count": 448, "self": 313.1579538139031, "children": { "TorchPPOOptimizer.update": { "total": 177.48711177709993, "count": 22809, "self": 177.48711177709993 } } } } } } }, "trainer_threads": { "total": 1.0349995136493817e-06, "count": 1, "self": 1.0349995136493817e-06 }, "TrainerController._save_models": { "total": 0.10374482099996385, "count": 1, "self": 0.001430348000212689, "children": { "RLTrainer._checkpoint": { "total": 0.10231447299975116, "count": 1, "self": 0.10231447299975116 } } } } } } }