{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.34081512689590454, "min": 0.34081512689590454, "max": 1.4689397811889648, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 10240.8125, "min": 10240.8125, "max": 44561.7578125, "count": 33 }, "Pyramids.Step.mean": { "value": 989949.0, "min": 29952.0, "max": 989949.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989949.0, "min": 29952.0, "max": 989949.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6192235946655273, "min": -0.11861501634120941, "max": 0.6900560855865479, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 172.1441650390625, "min": -28.315441131591797, "max": 201.4963836669922, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.012108786031603813, "min": -0.0018379880348220468, "max": 0.264141321182251, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.3662424087524414, "min": -0.5201506018638611, "max": 63.658058166503906, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06535187240330856, "min": 0.06522502676636492, "max": 0.07301841444859745, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9802780860496284, "min": 0.5001089330789387, "max": 1.055071909688801, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01614796205334749, "min": 0.0003226131672362488, "max": 0.016880532875629364, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.24221943080021235, "min": 0.003871358006834986, "max": 0.24221943080021235, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.426997524366668e-06, "min": 7.426997524366668e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011140496286550002, "min": 0.00011140496286550002, "max": 0.0035078732307089995, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10247563333333334, "min": 0.10247563333333334, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5371345, "min": 1.3886848, "max": 2.5692910000000007, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025731577000000005, "min": 0.00025731577000000005, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0038597365500000007, "min": 0.0038597365500000007, "max": 0.11695217089999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.011761984787881374, "min": 0.011761984787881374, "max": 0.4263363480567932, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.17642977833747864, "min": 0.16899797320365906, "max": 2.9843544960021973, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 296.7938144329897, "min": 273.4642857142857, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28789.0, "min": 15984.0, "max": 32973.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.663079154677689, "min": -1.0000000521540642, "max": 1.709147355587859, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 159.65559884905815, "min": -31.99760165810585, "max": 191.12719874829054, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.663079154677689, "min": -1.0000000521540642, "max": 1.709147355587859, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 159.65559884905815, "min": -31.99760165810585, "max": 191.12719874829054, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03601256066788968, "min": 0.03554546089165028, "max": 8.516976175829768, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.457205824117409, "min": 3.457205824117409, "max": 136.2716188132763, "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": "1681661264", "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": "1681663820" }, "total": 2555.623282707, "count": 1, "self": 1.1430191209997247, "children": { "run_training.setup": { "total": 0.21052543500036336, "count": 1, "self": 0.21052543500036336 }, "TrainerController.start_learning": { "total": 2554.2697381509997, "count": 1, "self": 1.8269112369225695, "children": { "TrainerController._reset_env": { "total": 4.660583152000072, "count": 1, "self": 4.660583152000072 }, "TrainerController.advance": { "total": 2547.6210044880772, "count": 64120, "self": 1.9124483490218154, "children": { "env_step": { "total": 1889.037927014041, "count": 64120, "self": 1760.1602294860554, "children": { "SubprocessEnvManager._take_step": { "total": 127.76284568197707, "count": 64120, "self": 5.392394715005594, "children": { "TorchPolicy.evaluate": { "total": 122.37045096697148, "count": 62564, "self": 122.37045096697148 } } }, "workers": { "total": 1.1148518460086052, "count": 64120, "self": 0.0, "children": { "worker_root": { "total": 2547.504733390888, "count": 64120, "is_parallel": true, "self": 920.1247763278197, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0026153869998779555, "count": 1, "is_parallel": true, "self": 0.0007612570002493158, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018541299996286398, "count": 8, "is_parallel": true, "self": 0.0018541299996286398 } } }, "UnityEnvironment.step": { "total": 0.05460824700003286, "count": 1, "is_parallel": true, "self": 0.000587169000027643, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005439550000119198, "count": 1, "is_parallel": true, "self": 0.0005439550000119198 }, "communicator.exchange": { "total": 0.05172550699990097, "count": 1, "is_parallel": true, "self": 0.05172550699990097 }, "steps_from_proto": { "total": 0.0017516160000923264, "count": 1, "is_parallel": true, "self": 0.00038191800013009924, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013696979999622272, "count": 8, "is_parallel": true, "self": 0.0013696979999622272 } } } } } } }, "UnityEnvironment.step": { "total": 1627.379957063068, "count": 64119, "is_parallel": true, "self": 36.29253537709883, "children": { "UnityEnvironment._generate_step_input": { "total": 25.375732487960704, "count": 64119, "is_parallel": true, "self": 25.375732487960704 }, "communicator.exchange": { "total": 1459.7741889320164, "count": 64119, "is_parallel": true, "self": 1459.7741889320164 }, "steps_from_proto": { "total": 105.93750026599218, "count": 64119, "is_parallel": true, "self": 23.666579687795547, "children": { "_process_rank_one_or_two_observation": { "total": 82.27092057819664, "count": 512952, "is_parallel": true, "self": 82.27092057819664 } } } } } } } } } } }, "trainer_advance": { "total": 656.6706291250143, "count": 64120, "self": 3.368529058968761, "children": { "process_trajectory": { "total": 115.05670586104952, "count": 64120, "self": 114.78296272804891, "children": { "RLTrainer._checkpoint": { "total": 0.2737431330006075, "count": 2, "self": 0.2737431330006075 } } }, "_update_policy": { "total": 538.245394204996, "count": 453, "self": 342.9147536460414, "children": { "TorchPPOOptimizer.update": { "total": 195.33064055895466, "count": 22770, "self": 195.33064055895466 } } } } } } }, "trainer_threads": { "total": 1.508999957877677e-06, "count": 1, "self": 1.508999957877677e-06 }, "TrainerController._save_models": { "total": 0.16123776499989617, "count": 1, "self": 0.0022992920003162, "children": { "RLTrainer._checkpoint": { "total": 0.15893847299957997, "count": 1, "self": 0.15893847299957997 } } } } } } }