{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.39278444647789, "min": 0.3806266188621521, "max": 1.446491003036499, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 11802.38671875, "min": 11339.6279296875, "max": 43880.75, "count": 33 }, "Pyramids.Step.mean": { "value": 989943.0, "min": 29952.0, "max": 989943.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989943.0, "min": 29952.0, "max": 989943.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5195940136909485, "min": -0.14950436353683472, "max": 0.6101991534233093, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 144.4471435546875, "min": -36.03055191040039, "max": 171.46595764160156, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.011042957194149494, "min": -0.02288067899644375, "max": 0.3780382573604584, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.069941997528076, "min": -6.223544597625732, "max": 91.10722351074219, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06673937001670267, "min": 0.06492917673445016, "max": 0.07400380942683012, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9343511802338375, "min": 0.5180266659878108, "max": 1.070502714963867, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015364833844484694, "min": 0.0016270437209681616, "max": 0.016112067339625873, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2151076738227857, "min": 0.02180253677689986, "max": 0.22556894275476225, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.559497480199998e-06, "min": 7.559497480199998e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010583296472279998, "min": 0.00010583296472279998, "max": 0.0035078189307270993, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10251979999999998, "min": 0.10251979999999998, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4352771999999998, "min": 1.3886848, "max": 2.5692729000000005, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002617280199999999, "min": 0.0002617280199999999, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036641922799999986, "min": 0.0036641922799999986, "max": 0.11695036271, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01091736275702715, "min": 0.01091736275702715, "max": 0.5549317002296448, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.15284307301044464, "min": 0.15284307301044464, "max": 3.884521961212158, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 361.13953488372096, "min": 335.07865168539325, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31058.0, "min": 15984.0, "max": 33133.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6388604490216387, "min": -1.0000000521540642, "max": 1.6424381834235084, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 140.94199861586094, "min": -29.16500174999237, "max": 146.17699832469225, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6388604490216387, "min": -1.0000000521540642, "max": 1.6424381834235084, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 140.94199861586094, "min": -29.16500174999237, "max": 146.17699832469225, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.040977215545480734, "min": 0.040977215545480734, "max": 11.740895867347717, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.5240405369113432, "min": 3.5240405369113432, "max": 187.85433387756348, "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": "1698055130", "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": "1698057382" }, "total": 2251.6610180609996, "count": 1, "self": 0.4755675909996171, "children": { "run_training.setup": { "total": 0.04264913899987732, "count": 1, "self": 0.04264913899987732 }, "TrainerController.start_learning": { "total": 2251.142801331, "count": 1, "self": 1.2884930579580214, "children": { "TrainerController._reset_env": { "total": 8.601933666999912, "count": 1, "self": 8.601933666999912 }, "TrainerController.advance": { "total": 2241.1807903570425, "count": 63973, "self": 1.367073860075834, "children": { "env_step": { "total": 1616.534791287982, "count": 63973, "self": 1485.1269635530532, "children": { "SubprocessEnvManager._take_step": { "total": 130.57796421193098, "count": 63973, "self": 4.52324459084798, "children": { "TorchPolicy.evaluate": { "total": 126.054719621083, "count": 62566, "self": 126.054719621083 } } }, "workers": { "total": 0.8298635229978117, "count": 63973, "self": 0.0, "children": { "worker_root": { "total": 2246.5180854650757, "count": 63973, "is_parallel": true, "self": 873.4525179910534, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005133394999802476, "count": 1, "is_parallel": true, "self": 0.003602686000022004, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015307089997804724, "count": 8, "is_parallel": true, "self": 0.0015307089997804724 } } }, "UnityEnvironment.step": { "total": 0.04780542899993634, "count": 1, "is_parallel": true, "self": 0.0006108409997978015, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00048078700001497054, "count": 1, "is_parallel": true, "self": 0.00048078700001497054 }, "communicator.exchange": { "total": 0.04512562300010359, "count": 1, "is_parallel": true, "self": 0.04512562300010359 }, "steps_from_proto": { "total": 0.0015881780000199797, "count": 1, "is_parallel": true, "self": 0.0003285549998963688, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012596230001236108, "count": 8, "is_parallel": true, "self": 0.0012596230001236108 } } } } } } }, "UnityEnvironment.step": { "total": 1373.0655674740224, "count": 63972, "is_parallel": true, "self": 34.28212932815336, "children": { "UnityEnvironment._generate_step_input": { "total": 24.112690912883636, "count": 63972, "is_parallel": true, "self": 24.112690912883636 }, "communicator.exchange": { "total": 1217.9407966379792, "count": 63972, "is_parallel": true, "self": 1217.9407966379792 }, "steps_from_proto": { "total": 96.72995059500613, "count": 63972, "is_parallel": true, "self": 19.142107524229232, "children": { "_process_rank_one_or_two_observation": { "total": 77.5878430707769, "count": 511776, "is_parallel": true, "self": 77.5878430707769 } } } } } } } } } } }, "trainer_advance": { "total": 623.2789252089844, "count": 63973, "self": 2.6293287830096688, "children": { "process_trajectory": { "total": 123.36865580296922, "count": 63973, "self": 123.15904870296913, "children": { "RLTrainer._checkpoint": { "total": 0.20960710000008476, "count": 2, "self": 0.20960710000008476 } } }, "_update_policy": { "total": 497.28094062300556, "count": 452, "self": 295.8223338260657, "children": { "TorchPPOOptimizer.update": { "total": 201.45860679693988, "count": 22812, "self": 201.45860679693988 } } } } } } }, "trainer_threads": { "total": 9.929999578162096e-07, "count": 1, "self": 9.929999578162096e-07 }, "TrainerController._save_models": { "total": 0.07158325599993987, "count": 1, "self": 0.0013586709992523538, "children": { "RLTrainer._checkpoint": { "total": 0.07022458500068751, "count": 1, "self": 0.07022458500068751 } } } } } } }