{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5681068301200867, "min": 0.5681068301200867, "max": 1.4420626163482666, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 17034.115234375, "min": 17034.115234375, "max": 43746.41015625, "count": 33 }, "Pyramids.Step.mean": { "value": 989986.0, "min": 29947.0, "max": 989986.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989986.0, "min": 29947.0, "max": 989986.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.3412111699581146, "min": -0.09827432781457901, "max": 0.40206193923950195, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 89.39732360839844, "min": -23.684112548828125, "max": 108.95878601074219, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.007717915344983339, "min": -0.027382386848330498, "max": 0.3422132730484009, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -2.0220937728881836, "min": -7.14680290222168, "max": 81.10454559326172, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06644598210049378, "min": 0.06520937134479811, "max": 0.0723510230574077, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9966897315074068, "min": 0.5698150683863924, "max": 1.0742209238718108, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01164217336158294, "min": 0.0009489312674346981, "max": 0.014105456371561603, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.1746326004237441, "min": 0.00948931267434698, "max": 0.19747638920186245, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.546837484420003e-06, "min": 7.546837484420003e-06, "max": 0.0002950140391619875, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011320256226630005, "min": 0.00011320256226630005, "max": 0.0035088938303688005, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10251558000000002, "min": 0.10251558000000002, "max": 0.1983380125, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5377337000000004, "min": 1.4781556000000002, "max": 2.5696312000000003, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002613064420000001, "min": 0.0002613064420000001, "max": 0.00983396744875, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003919596630000002, "min": 0.003919596630000002, "max": 0.11698615688, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.008664456196129322, "min": 0.008664456196129322, "max": 0.3869248628616333, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1299668401479721, "min": 0.12511391937732697, "max": 3.0953989028930664, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 524.6031746031746, "min": 449.4923076923077, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 33050.0, "min": 16874.0, "max": 33413.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.0943460051739027, "min": -0.9999871489501768, "max": 1.4581722854421688, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 68.94379832595587, "min": -30.999601617455482, "max": 94.78119855374098, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.0943460051739027, "min": -0.9999871489501768, "max": 1.4581722854421688, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 68.94379832595587, "min": -30.999601617455482, "max": 94.78119855374098, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04680416505901135, "min": 0.041866600723453586, "max": 8.089154235580388, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.9486623987177154, "min": 2.721329047024483, "max": 137.5156220048666, "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": "1689113490", "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": "1689115692" }, "total": 2202.127658621, "count": 1, "self": 0.8861614200009171, "children": { "run_training.setup": { "total": 0.039820418999852336, "count": 1, "self": 0.039820418999852336 }, "TrainerController.start_learning": { "total": 2201.2016767819996, "count": 1, "self": 1.383927276999657, "children": { "TrainerController._reset_env": { "total": 4.164244673999974, "count": 1, "self": 4.164244673999974 }, "TrainerController.advance": { "total": 2195.5025151899995, "count": 63550, "self": 1.3912653279780898, "children": { "env_step": { "total": 1528.205500737079, "count": 63550, "self": 1414.8180075501496, "children": { "SubprocessEnvManager._take_step": { "total": 112.60184838396503, "count": 63550, "self": 4.726478841980224, "children": { "TorchPolicy.evaluate": { "total": 107.87536954198481, "count": 62562, "self": 107.87536954198481 } } }, "workers": { "total": 0.785644802964498, "count": 63550, "self": 0.0, "children": { "worker_root": { "total": 2195.7268842569997, "count": 63550, "is_parallel": true, "self": 896.5040692079797, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0019162609999057167, "count": 1, "is_parallel": true, "self": 0.0005770889997620543, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013391720001436624, "count": 8, "is_parallel": true, "self": 0.0013391720001436624 } } }, "UnityEnvironment.step": { "total": 0.04831611399981739, "count": 1, "is_parallel": true, "self": 0.0005843779999850085, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004982640000434913, "count": 1, "is_parallel": true, "self": 0.0004982640000434913 }, "communicator.exchange": { "total": 0.04512135400000261, "count": 1, "is_parallel": true, "self": 0.04512135400000261 }, "steps_from_proto": { "total": 0.0021121179997862782, "count": 1, "is_parallel": true, "self": 0.00038708499982931244, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017250329999569658, "count": 8, "is_parallel": true, "self": 0.0017250329999569658 } } } } } } }, "UnityEnvironment.step": { "total": 1299.22281504902, "count": 63549, "is_parallel": true, "self": 33.30049478098431, "children": { "UnityEnvironment._generate_step_input": { "total": 22.271404307068224, "count": 63549, "is_parallel": true, "self": 22.271404307068224 }, "communicator.exchange": { "total": 1140.0931859650211, "count": 63549, "is_parallel": true, "self": 1140.0931859650211 }, "steps_from_proto": { "total": 103.55772999594637, "count": 63549, "is_parallel": true, "self": 19.886542000095687, "children": { "_process_rank_one_or_two_observation": { "total": 83.67118799585069, "count": 508392, "is_parallel": true, "self": 83.67118799585069 } } } } } } } } } } }, "trainer_advance": { "total": 665.9057491249423, "count": 63550, "self": 2.7218466049596373, "children": { "process_trajectory": { "total": 112.4122037049865, "count": 63550, "self": 112.14047624998648, "children": { "RLTrainer._checkpoint": { "total": 0.2717274550000184, "count": 2, "self": 0.2717274550000184 } } }, "_update_policy": { "total": 550.7716988149962, "count": 455, "self": 355.4554813659827, "children": { "TorchPPOOptimizer.update": { "total": 195.3162174490135, "count": 22797, "self": 195.3162174490135 } } } } } } }, "trainer_threads": { "total": 1.2300001799303573e-06, "count": 1, "self": 1.2300001799303573e-06 }, "TrainerController._save_models": { "total": 0.1509884110000712, "count": 1, "self": 0.0020852699999522883, "children": { "RLTrainer._checkpoint": { "total": 0.14890314100011892, "count": 1, "self": 0.14890314100011892 } } } } } } }