{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3947203457355499, "min": 0.38892829418182373, "max": 1.3436890840530396, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 11860.556640625, "min": 11686.517578125, "max": 40762.15234375, "count": 33 }, "Pyramids.Step.mean": { "value": 989991.0, "min": 29952.0, "max": 989991.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989991.0, "min": 29952.0, "max": 989991.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.41742685437202454, "min": -0.10730776935815811, "max": 0.4852939248085022, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 110.61811828613281, "min": -25.753864288330078, "max": 132.9705352783203, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.7464081048965454, "min": -0.7464081048965454, "max": 0.35799404978752136, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -197.7981414794922, "min": -197.7981414794922, "max": 84.84458923339844, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07154710434078167, "min": 0.06580170531863891, "max": 0.0746333875826427, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0016594607709433, "min": 0.5224337130784988, "max": 1.0710493366110743, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.08477951049822949, "min": 0.0001320869741731189, "max": 0.08477951049822949, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 1.1869131469752128, "min": 0.0018492176384236646, "max": 1.1869131469752128, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.388818965664284e-06, "min": 7.388818965664284e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010344346551929998, "min": 0.00010344346551929998, "max": 0.0035080814306395996, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10246290714285713, "min": 0.10246290714285713, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4344807, "min": 1.3886848, "max": 2.5693604000000008, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002560444235714285, "min": 0.0002560444235714285, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003584621929999999, "min": 0.003584621929999999, "max": 0.11695910396, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010311032645404339, "min": 0.009967285208404064, "max": 0.39173218607902527, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1443544626235962, "min": 0.13954199850559235, "max": 2.7421252727508545, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 437.59016393442624, "min": 375.075, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 26693.0, "min": 15984.0, "max": 32344.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.309525786027793, "min": -1.0000000521540642, "max": 1.5019456571266976, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 81.19059873372316, "min": -30.994601607322693, "max": 121.6575982272625, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.309525786027793, "min": -1.0000000521540642, "max": 1.5019456571266976, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 81.19059873372316, "min": -30.994601607322693, "max": 121.6575982272625, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04541650730196477, "min": 0.04220522576037587, "max": 7.776447342708707, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.8158234527218156, "min": 2.8158234527218156, "max": 124.42315748333931, "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": "1713367050", "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=Ml_Pyramids_wangila --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1713369414" }, "total": 2363.862040091, "count": 1, "self": 0.7053947929994138, "children": { "run_training.setup": { "total": 0.0661764620001577, "count": 1, "self": 0.0661764620001577 }, "TrainerController.start_learning": { "total": 2363.090468836, "count": 1, "self": 1.7013689439604605, "children": { "TrainerController._reset_env": { "total": 3.3875425339999765, "count": 1, "self": 3.3875425339999765 }, "TrainerController.advance": { "total": 2357.8988591670395, "count": 63637, "self": 1.6558543230667055, "children": { "env_step": { "total": 1688.5815161919866, "count": 63637, "self": 1536.228646861067, "children": { "SubprocessEnvManager._take_step": { "total": 151.31809497092536, "count": 63637, "self": 5.349655100824975, "children": { "TorchPolicy.evaluate": { "total": 145.96843987010038, "count": 62579, "self": 145.96843987010038 } } }, "workers": { "total": 1.0347743599941168, "count": 63637, "self": 0.0, "children": { "worker_root": { "total": 2357.2942018380713, "count": 63637, "is_parallel": true, "self": 962.156831297108, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.007922418999896763, "count": 1, "is_parallel": true, "self": 0.006381814999713242, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015406040001835208, "count": 8, "is_parallel": true, "self": 0.0015406040001835208 } } }, "UnityEnvironment.step": { "total": 0.049955782999859366, "count": 1, "is_parallel": true, "self": 0.0007247029998325161, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004413680001107423, "count": 1, "is_parallel": true, "self": 0.0004413680001107423 }, "communicator.exchange": { "total": 0.04697891599994364, "count": 1, "is_parallel": true, "self": 0.04697891599994364 }, "steps_from_proto": { "total": 0.0018107959999724699, "count": 1, "is_parallel": true, "self": 0.00038157499943736184, "children": { "_process_rank_one_or_two_observation": { "total": 0.001429221000535108, "count": 8, "is_parallel": true, "self": 0.001429221000535108 } } } } } } }, "UnityEnvironment.step": { "total": 1395.1373705409633, "count": 63636, "is_parallel": true, "self": 38.57945550997374, "children": { "UnityEnvironment._generate_step_input": { "total": 27.048135100956415, "count": 63636, "is_parallel": true, "self": 27.048135100956415 }, "communicator.exchange": { "total": 1213.8693087120428, "count": 63636, "is_parallel": true, "self": 1213.8693087120428 }, "steps_from_proto": { "total": 115.64047121799035, "count": 63636, "is_parallel": true, "self": 24.24394409689785, "children": { "_process_rank_one_or_two_observation": { "total": 91.3965271210925, "count": 509088, "is_parallel": true, "self": 91.3965271210925 } } } } } } } } } } }, "trainer_advance": { "total": 667.6614886519862, "count": 63637, "self": 3.1707147449606055, "children": { "process_trajectory": { "total": 138.43229713102687, "count": 63637, "self": 138.16347762002692, "children": { "RLTrainer._checkpoint": { "total": 0.26881951099994694, "count": 2, "self": 0.26881951099994694 } } }, "_update_policy": { "total": 526.0584767759988, "count": 451, "self": 309.0025048339685, "children": { "TorchPPOOptimizer.update": { "total": 217.05597194203028, "count": 22821, "self": 217.05597194203028 } } } } } } }, "trainer_threads": { "total": 1.1880001693498343e-06, "count": 1, "self": 1.1880001693498343e-06 }, "TrainerController._save_models": { "total": 0.10269700299977558, "count": 1, "self": 0.001743661999626056, "children": { "RLTrainer._checkpoint": { "total": 0.10095334100014952, "count": 1, "self": 0.10095334100014952 } } } } } } }