{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.38705477118492126, "min": 0.38705477118492126, "max": 1.4497146606445312, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 11568.29296875, "min": 11568.29296875, "max": 43978.54296875, "count": 33 }, "Pyramids.Step.mean": { "value": 989916.0, "min": 29952.0, "max": 989916.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989916.0, "min": 29952.0, "max": 989916.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5668317675590515, "min": -0.09749218076467514, "max": 0.5825629830360413, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 157.5792236328125, "min": -23.495615005493164, "max": 163.7001953125, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.10332465171813965, "min": -0.009386347606778145, "max": 0.2316073328256607, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 28.724252700805664, "min": -2.637563705444336, "max": 56.048973083496094, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06916791010427573, "min": 0.06520018119070276, "max": 0.07276354251412932, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9683507414598601, "min": 0.47710298022757763, "max": 1.0345621708228125, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016374589622699647, "min": 0.00042985574641544593, "max": 0.017182838841679267, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.22924425471779505, "min": 0.004298557464154459, "max": 0.2522649444373183, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.51426178099286e-06, "min": 7.51426178099286e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010519966493390004, "min": 0.00010519966493390004, "max": 0.0032526068157978, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10250472142857145, "min": 0.10250472142857145, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4350661000000002, "min": 1.3886848, "max": 2.4441183, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002602216707142858, "min": 0.0002602216707142858, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003643103390000001, "min": 0.003643103390000001, "max": 0.10844179978000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009915276430547237, "min": 0.009915276430547237, "max": 0.38046422600746155, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.13881386816501617, "min": 0.13881386816501617, "max": 2.6632494926452637, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 329.97727272727275, "min": 320.38709677419354, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29038.0, "min": 15984.0, "max": 34089.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.580952790680896, "min": -1.0000000521540642, "max": 1.6163247052219607, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 140.70479837059975, "min": -31.99920167028904, "max": 150.31819758564234, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.580952790680896, "min": -1.0000000521540642, "max": 1.6163247052219607, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 140.70479837059975, "min": -31.99920167028904, "max": 150.31819758564234, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03395346064726153, "min": 0.03395346064726153, "max": 7.416145252995193, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.0218579976062756, "min": 3.0141490271198563, "max": 118.65832404792309, "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": "1681597394", "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": "1681599635" }, "total": 2241.2508032779997, "count": 1, "self": 0.5366386839996267, "children": { "run_training.setup": { "total": 0.19752263400005177, "count": 1, "self": 0.19752263400005177 }, "TrainerController.start_learning": { "total": 2240.51664196, "count": 1, "self": 1.5175431739098713, "children": { "TrainerController._reset_env": { "total": 3.8224710769998183, "count": 1, "self": 3.8224710769998183 }, "TrainerController.advance": { "total": 2235.0805829460896, "count": 63928, "self": 1.5192536830463723, "children": { "env_step": { "total": 1614.1665202900151, "count": 63928, "self": 1500.6824397960117, "children": { "SubprocessEnvManager._take_step": { "total": 112.57450150005025, "count": 63928, "self": 5.041566240054863, "children": { "TorchPolicy.evaluate": { "total": 107.53293525999538, "count": 62565, "self": 107.53293525999538 } } }, "workers": { "total": 0.9095789939531187, "count": 63928, "self": 0.0, "children": { "worker_root": { "total": 2235.1159772520105, "count": 63928, "is_parallel": true, "self": 853.977492849081, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001855008999882557, "count": 1, "is_parallel": true, "self": 0.000626796999540602, "children": { "_process_rank_one_or_two_observation": { "total": 0.001228212000341955, "count": 8, "is_parallel": true, "self": 0.001228212000341955 } } }, "UnityEnvironment.step": { "total": 0.04473271000006207, "count": 1, "is_parallel": true, "self": 0.0005064330000550399, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003662879998955759, "count": 1, "is_parallel": true, "self": 0.0003662879998955759 }, "communicator.exchange": { "total": 0.04219315899990761, "count": 1, "is_parallel": true, "self": 0.04219315899990761 }, "steps_from_proto": { "total": 0.001666830000203845, "count": 1, "is_parallel": true, "self": 0.00036590500030797557, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013009249998958694, "count": 8, "is_parallel": true, "self": 0.0013009249998958694 } } } } } } }, "UnityEnvironment.step": { "total": 1381.1384844029294, "count": 63927, "is_parallel": true, "self": 33.489793747997965, "children": { "UnityEnvironment._generate_step_input": { "total": 25.290703428001734, "count": 63927, "is_parallel": true, "self": 25.290703428001734 }, "communicator.exchange": { "total": 1220.6281484799813, "count": 63927, "is_parallel": true, "self": 1220.6281484799813 }, "steps_from_proto": { "total": 101.72983874694842, "count": 63927, "is_parallel": true, "self": 22.3537660358827, "children": { "_process_rank_one_or_two_observation": { "total": 79.37607271106572, "count": 511416, "is_parallel": true, "self": 79.37607271106572 } } } } } } } } } } }, "trainer_advance": { "total": 619.3948089730284, "count": 63928, "self": 2.683822071048553, "children": { "process_trajectory": { "total": 112.97428828997931, "count": 63928, "self": 112.75971316797973, "children": { "RLTrainer._checkpoint": { "total": 0.21457512199958728, "count": 2, "self": 0.21457512199958728 } } }, "_update_policy": { "total": 503.7366986120005, "count": 449, "self": 322.7968503980187, "children": { "TorchPPOOptimizer.update": { "total": 180.9398482139818, "count": 22854, "self": 180.9398482139818 } } } } } } }, "trainer_threads": { "total": 9.230002433469053e-07, "count": 1, "self": 9.230002433469053e-07 }, "TrainerController._save_models": { "total": 0.09604384000022037, "count": 1, "self": 0.0015314080005737196, "children": { "RLTrainer._checkpoint": { "total": 0.09451243199964665, "count": 1, "self": 0.09451243199964665 } } } } } } }