{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4230779707431793, "min": 0.42147529125213623, "max": 1.5254312753677368, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 12787.1083984375, "min": 12509.38671875, "max": 46275.484375, "count": 33 }, "Pyramids.Step.mean": { "value": 989927.0, "min": 29952.0, "max": 989927.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989927.0, "min": 29952.0, "max": 989927.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.4729638993740082, "min": -0.10377603024244308, "max": 0.5280724167823792, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 128.1732177734375, "min": -25.113800048828125, "max": 145.74798583984375, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.04564893990755081, "min": -0.04564893990755081, "max": 0.22620101273059845, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -12.37086296081543, "min": -12.37086296081543, "max": 54.514442443847656, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06945383235708706, "min": 0.06616144583718479, "max": 0.07272259248335812, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.041807485356306, "min": 0.4925468528868053, "max": 1.0425383582695242, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015391864183604614, "min": 0.0003842888179143174, "max": 0.015391864183604614, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.23087796275406922, "min": 0.004995754632886126, "max": 0.23087796275406922, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.489997503366667e-06, "min": 7.489997503366667e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001123499625505, "min": 0.0001123499625505, "max": 0.0033761851746049996, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10249663333333334, "min": 0.10249663333333334, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5374495000000001, "min": 1.3886848, "max": 2.4439306000000003, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025941367000000004, "min": 0.00025941367000000004, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0038912050500000007, "min": 0.0038912050500000007, "max": 0.11255696049999998, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.011395227164030075, "min": 0.011395227164030075, "max": 0.28998467326164246, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.17092840373516083, "min": 0.16609740257263184, "max": 2.029892683029175, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 384.65432098765433, "min": 364.4691358024691, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31157.0, "min": 15984.0, "max": 33416.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5165431946516037, "min": -1.0000000521540642, "max": 1.6108271394062925, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 122.8399987667799, "min": -31.994401663541794, "max": 130.4769982919097, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5165431946516037, "min": -1.0000000521540642, "max": 1.6108271394062925, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 122.8399987667799, "min": -31.994401663541794, "max": 130.4769982919097, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04509838224808329, "min": 0.04509838224808329, "max": 5.46549166738987, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.6529689620947465, "min": 3.615344223449938, "max": 87.44786667823792, "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": "1679066778", "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": "1679068979" }, "total": 2201.450342607, "count": 1, "self": 0.4808456850005314, "children": { "run_training.setup": { "total": 0.10520746999964103, "count": 1, "self": 0.10520746999964103 }, "TrainerController.start_learning": { "total": 2200.864289452, "count": 1, "self": 1.6215892817272106, "children": { "TrainerController._reset_env": { "total": 5.786552279999796, "count": 1, "self": 5.786552279999796 }, "TrainerController.advance": { "total": 2193.359693119273, "count": 63617, "self": 1.677123789108009, "children": { "env_step": { "total": 1554.9728668789694, "count": 63617, "self": 1432.5549379081758, "children": { "SubprocessEnvManager._take_step": { "total": 121.44956789089974, "count": 63617, "self": 5.122897880767596, "children": { "TorchPolicy.evaluate": { "total": 116.32667001013215, "count": 62570, "self": 116.32667001013215 } } }, "workers": { "total": 0.9683610798938389, "count": 63617, "self": 0.0, "children": { "worker_root": { "total": 2195.2138734220375, "count": 63617, "is_parallel": true, "self": 891.0899120200133, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018522609998399275, "count": 1, "is_parallel": true, "self": 0.0006118069991316588, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012404540007082687, "count": 8, "is_parallel": true, "self": 0.0012404540007082687 } } }, "UnityEnvironment.step": { "total": 0.04630823400020745, "count": 1, "is_parallel": true, "self": 0.0005315100002007966, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004568089998429059, "count": 1, "is_parallel": true, "self": 0.0004568089998429059 }, "communicator.exchange": { "total": 0.04368492699995841, "count": 1, "is_parallel": true, "self": 0.04368492699995841 }, "steps_from_proto": { "total": 0.0016349880002053396, "count": 1, "is_parallel": true, "self": 0.00043710200043278746, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011978859997725522, "count": 8, "is_parallel": true, "self": 0.0011978859997725522 } } } } } } }, "UnityEnvironment.step": { "total": 1304.1239614020242, "count": 63616, "is_parallel": true, "self": 32.39869983703966, "children": { "UnityEnvironment._generate_step_input": { "total": 24.609903433062755, "count": 63616, "is_parallel": true, "self": 24.609903433062755 }, "communicator.exchange": { "total": 1147.2167925740036, "count": 63616, "is_parallel": true, "self": 1147.2167925740036 }, "steps_from_proto": { "total": 99.89856555791812, "count": 63616, "is_parallel": true, "self": 22.18951584902561, "children": { "_process_rank_one_or_two_observation": { "total": 77.70904970889251, "count": 508928, "is_parallel": true, "self": 77.70904970889251 } } } } } } } } } } }, "trainer_advance": { "total": 636.7097024511954, "count": 63617, "self": 3.0650607710940676, "children": { "process_trajectory": { "total": 125.77981974011709, "count": 63617, "self": 125.5140645621168, "children": { "RLTrainer._checkpoint": { "total": 0.26575517800029047, "count": 2, "self": 0.26575517800029047 } } }, "_update_policy": { "total": 507.86482193998427, "count": 444, "self": 321.2221861749831, "children": { "TorchPPOOptimizer.update": { "total": 186.64263576500116, "count": 22791, "self": 186.64263576500116 } } } } } } }, "trainer_threads": { "total": 8.850001904647797e-07, "count": 1, "self": 8.850001904647797e-07 }, "TrainerController._save_models": { "total": 0.09645388599983562, "count": 1, "self": 0.0014436469991778722, "children": { "RLTrainer._checkpoint": { "total": 0.09501023900065775, "count": 1, "self": 0.09501023900065775 } } } } } } }