{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4394199848175049, "min": 0.43576881289482117, "max": 1.436813235282898, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 13309.15234375, "min": 12961.5078125, "max": 43587.16796875, "count": 33 }, "Pyramids.Step.mean": { "value": 989949.0, "min": 29939.0, "max": 989949.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989949.0, "min": 29939.0, "max": 989949.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.32521969079971313, "min": -0.151437908411026, "max": 0.36951524019241333, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 84.23190307617188, "min": -36.03480911254883, "max": 97.18251037597656, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.215140700340271, "min": -0.215140700340271, "max": 0.4236548840999603, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -55.72144317626953, "min": -55.72144317626953, "max": 100.40620422363281, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0689723463690708, "min": 0.06636317444023486, "max": 0.07237280837681882, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9656128491669912, "min": 0.5066096586377318, "max": 1.0703955069184303, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.022408789294394067, "min": 0.0008289831317047771, "max": 0.022408789294394067, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.3137230501215169, "min": 0.011605763843866879, "max": 0.3137230501215169, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.470783224057143e-06, "min": 7.470783224057143e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001045909651368, "min": 0.0001045909651368, "max": 0.003510825229724999, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10249022857142856, "min": 0.10249022857142856, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4348632, "min": 1.3886848, "max": 2.5702750000000005, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025877383428571425, "min": 0.00025877383428571425, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036228336799999997, "min": 0.0036228336799999997, "max": 0.11705047249999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.018394289538264275, "min": 0.018394289538264275, "max": 0.5522270798683167, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.25752004981040955, "min": 0.25752004981040955, "max": 3.8655893802642822, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 533.9454545454546, "min": 461.93939393939394, "max": 992.1176470588235, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29367.0, "min": 16866.0, "max": 32144.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.1800392606694783, "min": -0.9105125488713384, "max": 1.3238768922594877, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 66.08219859749079, "min": -29.136401563882828, "max": 86.0519979968667, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.1800392606694783, "min": -0.9105125488713384, "max": 1.3238768922594877, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 66.08219859749079, "min": -29.136401563882828, "max": 86.0519979968667, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.10050944155799309, "min": 0.0901295617607852, "max": 10.837626076796475, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 5.6285287272476126, "min": 5.6285287272476126, "max": 184.23964330554008, "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": "1681293158", "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": "1681295200" }, "total": 2041.7107992919996, "count": 1, "self": 0.4748003899994728, "children": { "run_training.setup": { "total": 0.17428825399974812, "count": 1, "self": 0.17428825399974812 }, "TrainerController.start_learning": { "total": 2041.0617106480004, "count": 1, "self": 1.374537877944931, "children": { "TrainerController._reset_env": { "total": 4.473501295999995, "count": 1, "self": 4.473501295999995 }, "TrainerController.advance": { "total": 2035.114706293055, "count": 63505, "self": 1.407388960004937, "children": { "env_step": { "total": 1424.1374075239764, "count": 63505, "self": 1318.423122392022, "children": { "SubprocessEnvManager._take_step": { "total": 104.86183132200222, "count": 63505, "self": 4.667152993994478, "children": { "TorchPolicy.evaluate": { "total": 100.19467832800774, "count": 62571, "self": 100.19467832800774 } } }, "workers": { "total": 0.8524538099522943, "count": 63505, "self": 0.0, "children": { "worker_root": { "total": 2036.209034784049, "count": 63505, "is_parallel": true, "self": 827.7204428611312, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002628277999974671, "count": 1, "is_parallel": true, "self": 0.0007775689991831314, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018507090007915394, "count": 8, "is_parallel": true, "self": 0.0018507090007915394 } } }, "UnityEnvironment.step": { "total": 0.05971577999980582, "count": 1, "is_parallel": true, "self": 0.000523820000125852, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004575190000650764, "count": 1, "is_parallel": true, "self": 0.0004575190000650764 }, "communicator.exchange": { "total": 0.056991263999861985, "count": 1, "is_parallel": true, "self": 0.056991263999861985 }, "steps_from_proto": { "total": 0.0017431769997529045, "count": 1, "is_parallel": true, "self": 0.0003983069996138511, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013448700001390534, "count": 8, "is_parallel": true, "self": 0.0013448700001390534 } } } } } } }, "UnityEnvironment.step": { "total": 1208.4885919229177, "count": 63504, "is_parallel": true, "self": 31.989826823958538, "children": { "UnityEnvironment._generate_step_input": { "total": 22.575828650937183, "count": 63504, "is_parallel": true, "self": 22.575828650937183 }, "communicator.exchange": { "total": 1061.5763531529947, "count": 63504, "is_parallel": true, "self": 1061.5763531529947 }, "steps_from_proto": { "total": 92.34658329502736, "count": 63504, "is_parallel": true, "self": 19.5437134210124, "children": { "_process_rank_one_or_two_observation": { "total": 72.80286987401496, "count": 508032, "is_parallel": true, "self": 72.80286987401496 } } } } } } } } } } }, "trainer_advance": { "total": 609.5699098090736, "count": 63505, "self": 2.5793742401024247, "children": { "process_trajectory": { "total": 103.83068366097314, "count": 63505, "self": 103.60240765597337, "children": { "RLTrainer._checkpoint": { "total": 0.22827600499977052, "count": 2, "self": 0.22827600499977052 } } }, "_update_policy": { "total": 503.159851907998, "count": 456, "self": 322.7716608240221, "children": { "TorchPPOOptimizer.update": { "total": 180.38819108397593, "count": 22770, "self": 180.38819108397593 } } } } } } }, "trainer_threads": { "total": 9.430004865862429e-07, "count": 1, "self": 9.430004865862429e-07 }, "TrainerController._save_models": { "total": 0.09896423800000775, "count": 1, "self": 0.0014460660004260717, "children": { "RLTrainer._checkpoint": { "total": 0.09751817199958168, "count": 1, "self": 0.09751817199958168 } } } } } } }