{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3391072750091553, "min": 0.3391072750091553, "max": 1.4705822467803955, "count": 36 }, "Pyramids.Policy.Entropy.sum": { "value": 10205.7724609375, "min": 10205.7724609375, "max": 44611.58203125, "count": 36 }, "Pyramids.Step.mean": { "value": 1079998.0, "min": 29952.0, "max": 1079998.0, "count": 36 }, "Pyramids.Step.sum": { "value": 1079998.0, "min": 29952.0, "max": 1079998.0, "count": 36 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5946340560913086, "min": -0.09426271170377731, "max": 0.73419189453125, "count": 36 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 164.11900329589844, "min": -22.623050689697266, "max": 218.05499267578125, "count": 36 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.023516779765486717, "min": -0.016939524561166763, "max": 0.19763316214084625, "count": 36 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 6.490631103515625, "min": -4.607550621032715, "max": 47.62959289550781, "count": 36 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06748371846158337, "min": 0.06539317868258322, "max": 0.0740504807247566, "count": 36 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.944772058462167, "min": 0.5038601152985905, "max": 1.043509123921075, "count": 36 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01411561726538513, "min": 0.00013149275955771496, "max": 0.01599169017018063, "count": 36 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.1976186417153918, "min": 0.0017094058742502945, "max": 0.22388366238252883, "count": 36 }, "Pyramids.Policy.LearningRate.mean": { "value": 0.00019343574980714285, "min": 0.00019343574980714285, "max": 0.00029838354339596195, "count": 36 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0027081004973, "min": 0.0020886848037717336, "max": 0.003758846847051099, "count": 36 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.16447857142857145, "min": 0.16447857142857145, "max": 0.19946118095238097, "count": 36 }, "Pyramids.Policy.Epsilon.sum": { "value": 2.3027, "min": 1.3962282666666668, "max": 2.707319866666667, "count": 36 }, "Pyramids.Policy.Beta.mean": { "value": 0.006451409285714286, "min": 0.006451409285714286, "max": 0.009946171977142856, "count": 36 }, "Pyramids.Policy.Beta.sum": { "value": 0.09031973000000001, "min": 0.06962320384, "max": 0.12530959510999998, "count": 36 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.007875731214880943, "min": 0.007746386341750622, "max": 0.32836344838142395, "count": 36 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.11026023328304291, "min": 0.11026023328304291, "max": 2.29854416847229, "count": 36 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 316.7391304347826, "min": 265.85714285714283, "max": 999.0, "count": 36 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29140.0, "min": 15984.0, "max": 32796.0, "count": 36 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.552780418049382, "min": -1.0000000521540642, "max": 1.7137961762292044, "count": 36 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 142.85579846054316, "min": -31.998001664876938, "max": 189.73299758136272, "count": 36 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.552780418049382, "min": -1.0000000521540642, "max": 1.7137961762292044, "count": 36 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 142.85579846054316, "min": -31.998001664876938, "max": 189.73299758136272, "count": 36 }, "Pyramids.Policy.RndReward.mean": { "value": 0.026204802018701626, "min": 0.02373494691758727, "max": 6.8889878103509545, "count": 36 }, "Pyramids.Policy.RndReward.sum": { "value": 2.4108417857205495, "min": 2.4108417857205495, "max": 110.22380496561527, "count": 36 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 36 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 36 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1777899311", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1777901884" }, "total": 2573.316311529, "count": 1, "self": 0.4804717530000744, "children": { "run_training.setup": { "total": 0.032270942000195646, "count": 1, "self": 0.032270942000195646 }, "TrainerController.start_learning": { "total": 2572.8035688339996, "count": 1, "self": 1.7507246479135574, "children": { "TrainerController._reset_env": { "total": 2.709788586999821, "count": 1, "self": 2.709788586999821 }, "TrainerController.advance": { "total": 2568.3430166720855, "count": 69793, "self": 1.8370316160426228, "children": { "env_step": { "total": 1813.4777402910618, "count": 69793, "self": 1627.8563426960263, "children": { "SubprocessEnvManager._take_step": { "total": 184.55625325005303, "count": 69793, "self": 5.559302501055754, "children": { "TorchPolicy.evaluate": { "total": 178.99695074899728, "count": 68293, "self": 178.99695074899728 } } }, "workers": { "total": 1.0651443449824, "count": 69793, "self": 0.0, "children": { "worker_root": { "total": 2564.786573260946, "count": 69793, "is_parallel": true, "self": 1081.0698453068553, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018557930002316425, "count": 1, "is_parallel": true, "self": 0.0006128820000412816, "children": { "_process_rank_one_or_two_observation": { "total": 0.001242911000190361, "count": 8, "is_parallel": true, "self": 0.001242911000190361 } } }, "UnityEnvironment.step": { "total": 0.1014686039998196, "count": 1, "is_parallel": true, "self": 0.0005422629997156037, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005040500000177417, "count": 1, "is_parallel": true, "self": 0.0005040500000177417 }, "communicator.exchange": { "total": 0.09674727500032532, "count": 1, "is_parallel": true, "self": 0.09674727500032532 }, "steps_from_proto": { "total": 0.0036750159997609444, "count": 1, "is_parallel": true, "self": 0.0003933400003006682, "children": { "_process_rank_one_or_two_observation": { "total": 0.003281675999460276, "count": 8, "is_parallel": true, "self": 0.003281675999460276 } } } } } } }, "UnityEnvironment.step": { "total": 1483.7167279540909, "count": 69792, "is_parallel": true, "self": 40.23797356623527, "children": { "UnityEnvironment._generate_step_input": { "total": 27.537660208908164, "count": 69792, "is_parallel": true, "self": 27.537660208908164 }, "communicator.exchange": { "total": 1284.2098969579051, "count": 69792, "is_parallel": true, "self": 1284.2098969579051 }, "steps_from_proto": { "total": 131.7311972210423, "count": 69792, "is_parallel": true, "self": 27.64486695784717, "children": { "_process_rank_one_or_two_observation": { "total": 104.08633026319512, "count": 558336, "is_parallel": true, "self": 104.08633026319512 } } } } } } } } } } }, "trainer_advance": { "total": 753.0282447649811, "count": 69793, "self": 3.18206963782859, "children": { "process_trajectory": { "total": 145.73731562413877, "count": 69793, "self": 145.52402623513854, "children": { "RLTrainer._checkpoint": { "total": 0.21328938900023786, "count": 2, "self": 0.21328938900023786 } } }, "_update_policy": { "total": 604.1088595030137, "count": 489, "self": 333.8845639101137, "children": { "TorchPPOOptimizer.update": { "total": 270.22429559290003, "count": 24951, "self": 270.22429559290003 } } } } } } }, "trainer_threads": { "total": 1.2390000847517513e-06, "count": 1, "self": 1.2390000847517513e-06 }, "TrainerController._save_models": { "total": 3.76880007024738e-05, "count": 1, "self": 2.064400086965179e-05, "children": { "RLTrainer._checkpoint": { "total": 1.704399983282201e-05, "count": 1, "self": 1.704399983282201e-05 } } } } } } }