{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.1280280351638794, "min": 0.1280280351638794, "max": 1.404155969619751, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 3832.647216796875, "min": 3832.647216796875, "max": 42596.4765625, "count": 100 }, "Pyramids.Step.mean": { "value": 2999958.0, "min": 29931.0, "max": 2999958.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999958.0, "min": 29931.0, "max": 2999958.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6445729732513428, "min": -0.10107990354299545, "max": 0.8103000521659851, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 184.34786987304688, "min": -24.36025619506836, "max": 245.5209197998047, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.0012540265452116728, "min": -0.02054331637918949, "max": 0.5019341707229614, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 0.35865160822868347, "min": -5.505609035491943, "max": 118.9583969116211, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06852440867218886, "min": 0.06322094414967533, "max": 0.07317409071724937, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.959341721410644, "min": 0.5738047045346907, "max": 1.0887227959145662, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.012928899565210412, "min": 0.00018410205765735974, "max": 0.016045707431421304, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.18100459391294577, "min": 0.0023933267495456767, "max": 0.22463990403989825, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.435742378595239e-06, "min": 1.435742378595239e-06, "max": 0.00029833901305366254, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.0100393300333345e-05, "min": 2.0100393300333345e-05, "max": 0.003969336876887733, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10047854761904762, "min": 0.10047854761904762, "max": 0.19944633750000001, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4066996666666667, "min": 1.4066996666666667, "max": 2.7675197333333337, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 5.780690714285718e-05, "min": 5.780690714285718e-05, "max": 0.009944689116249999, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.0008092967000000005, "min": 0.0008092967000000005, "max": 0.13231891544000002, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.005249980371445417, "min": 0.005136231891810894, "max": 0.4665215015411377, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.07349972426891327, "min": 0.07315721362829208, "max": 3.7321720123291016, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 278.9252336448598, "min": 226.70992366412213, "max": 999.0, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29845.0, "min": 16858.0, "max": 33234.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6264188530028991, "min": -0.9998875516466796, "max": 1.7732900602899435, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 172.4003984183073, "min": -31.99640165269375, "max": 232.3009978979826, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6264188530028991, "min": -0.9998875516466796, "max": 1.7732900602899435, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 172.4003984183073, "min": -31.99640165269375, "max": 232.3009978979826, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.015191961437456072, "min": 0.013034798315204573, "max": 9.293924428084317, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 1.6103479123703437, "min": 1.5957335580096697, "max": 157.9967152774334, "count": 100 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1704371667", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.2+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1704379590" }, "total": 7923.340414650001, "count": 1, "self": 0.5440078849997008, "children": { "run_training.setup": { "total": 0.08972859200002858, "count": 1, "self": 0.08972859200002858 }, "TrainerController.start_learning": { "total": 7922.706678173001, "count": 1, "self": 5.43626541024787, "children": { "TrainerController._reset_env": { "total": 3.9893678129999444, "count": 1, "self": 3.9893678129999444 }, "TrainerController.advance": { "total": 7913.189031073752, "count": 194173, "self": 5.732882100500319, "children": { "env_step": { "total": 5889.996556101192, "count": 194173, "self": 5430.175777567135, "children": { "SubprocessEnvManager._take_step": { "total": 456.57297231906375, "count": 194173, "self": 16.489195459105645, "children": { "TorchPolicy.evaluate": { "total": 440.0837768599581, "count": 187558, "self": 440.0837768599581 } } }, "workers": { "total": 3.247806214993261, "count": 194173, "self": 0.0, "children": { "worker_root": { "total": 7903.844115508068, "count": 194173, "is_parallel": true, "self": 2901.592211454862, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006417387000055896, "count": 1, "is_parallel": true, "self": 0.004439743000148155, "children": { "_process_rank_one_or_two_observation": { "total": 0.001977643999907741, "count": 8, "is_parallel": true, "self": 0.001977643999907741 } } }, "UnityEnvironment.step": { "total": 0.05925521000006029, "count": 1, "is_parallel": true, "self": 0.003827479000051426, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005553869999630479, "count": 1, "is_parallel": true, "self": 0.0005553869999630479 }, "communicator.exchange": { "total": 0.052968188000022565, "count": 1, "is_parallel": true, "self": 0.052968188000022565 }, "steps_from_proto": { "total": 0.0019041560000232494, "count": 1, "is_parallel": true, "self": 0.000421396999740864, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014827590002823854, "count": 8, "is_parallel": true, "self": 0.0014827590002823854 } } } } } } }, "UnityEnvironment.step": { "total": 5002.251904053206, "count": 194172, "is_parallel": true, "self": 117.65977633332841, "children": { "UnityEnvironment._generate_step_input": { "total": 80.76340095779892, "count": 194172, "is_parallel": true, "self": 80.76340095779892 }, "communicator.exchange": { "total": 4461.14197293298, "count": 194172, "is_parallel": true, "self": 4461.14197293298 }, "steps_from_proto": { "total": 342.6867538290986, "count": 194172, "is_parallel": true, "self": 73.08192771666347, "children": { "_process_rank_one_or_two_observation": { "total": 269.60482611243515, "count": 1553376, "is_parallel": true, "self": 269.60482611243515 } } } } } } } } } } }, "trainer_advance": { "total": 2017.4595928720594, "count": 194173, "self": 10.115866971120113, "children": { "process_trajectory": { "total": 428.7060503129528, "count": 194173, "self": 428.081679701952, "children": { "RLTrainer._checkpoint": { "total": 0.6243706110008134, "count": 6, "self": 0.6243706110008134 } } }, "_update_policy": { "total": 1578.6376755879865, "count": 1401, "self": 938.1529130960686, "children": { "TorchPPOOptimizer.update": { "total": 640.4847624919179, "count": 68382, "self": 640.4847624919179 } } } } } } }, "trainer_threads": { "total": 8.799997885944322e-07, "count": 1, "self": 8.799997885944322e-07 }, "TrainerController._save_models": { "total": 0.09201299600135826, "count": 1, "self": 0.0017892300002131378, "children": { "RLTrainer._checkpoint": { "total": 0.09022376600114512, "count": 1, "self": 0.09022376600114512 } } } } } } }