{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.36157143115997314, "min": 0.3592761158943176, "max": 1.4545283317565918, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 10887.638671875, "min": 10812.7744140625, "max": 44124.5703125, "count": 33 }, "Pyramids.Step.mean": { "value": 989924.0, "min": 29902.0, "max": 989924.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989924.0, "min": 29902.0, "max": 989924.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5999639630317688, "min": -0.13866865634918213, "max": 0.6500394344329834, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 167.3899383544922, "min": -33.00313949584961, "max": 187.2113494873047, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.03151479363441467, "min": -0.01749282516539097, "max": 0.30873727798461914, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 8.792627334594727, "min": -5.037933826446533, "max": 73.4794692993164, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06636647236744118, "min": 0.06483748087789751, "max": 0.07158446299514298, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9291306131441767, "min": 0.4880446261633823, "max": 1.047673749504611, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.013954396296737418, "min": 0.0009856462528282858, "max": 0.015372815381342457, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.19536154815432386, "min": 0.013799047539596002, "max": 0.2152194153387944, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.471126081085712e-06, "min": 7.471126081085712e-06, "max": 0.00029523505873117143, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010459576513519996, "min": 0.00010459576513519996, "max": 0.0037605448464851, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10249034285714287, "min": 0.10249034285714287, "max": 0.19841168571428572, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4348648000000002, "min": 1.3888818, "max": 2.6535149000000002, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025878525142857136, "min": 0.00025878525142857136, "max": 0.009841327402857142, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003622993519999999, "min": 0.003622993519999999, "max": 0.12536613851, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.012087264098227024, "min": 0.012087264098227024, "max": 0.3987515866756439, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1692216992378235, "min": 0.1692216992378235, "max": 2.7912611961364746, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 293.01, "min": 293.01, "max": 989.6129032258065, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29301.0, "min": 17084.0, "max": 32538.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7072475015526951, "min": -0.8566933840513229, "max": 1.7072475015526951, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 172.4319976568222, "min": -28.158801659941673, "max": 176.37219781428576, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7072475015526951, "min": -0.8566933840513229, "max": 1.7072475015526951, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 172.4319976568222, "min": -28.158801659941673, "max": 176.37219781428576, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03669696707450808, "min": 0.03669696707450808, "max": 6.840406454685661, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.706393674525316, "min": 3.706393674525316, "max": 123.12731618434191, "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": "1739955867", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1739958136" }, "total": 2268.8213013179998, "count": 1, "self": 0.4771902179995777, "children": { "run_training.setup": { "total": 0.01990708299990729, "count": 1, "self": 0.01990708299990729 }, "TrainerController.start_learning": { "total": 2268.3242040170003, "count": 1, "self": 1.3362652679379607, "children": { "TrainerController._reset_env": { "total": 2.0897173049997946, "count": 1, "self": 2.0897173049997946 }, "TrainerController.advance": { "total": 2264.795264996063, "count": 64061, "self": 1.4185678959161123, "children": { "env_step": { "total": 1594.7375583660119, "count": 64061, "self": 1442.8241301451485, "children": { "SubprocessEnvManager._take_step": { "total": 151.1471358699314, "count": 64061, "self": 4.633315160974689, "children": { "TorchPolicy.evaluate": { "total": 146.5138207089567, "count": 62567, "self": 146.5138207089567 } } }, "workers": { "total": 0.7662923509319626, "count": 64061, "self": 0.0, "children": { "worker_root": { "total": 2263.5375376559905, "count": 64061, "is_parallel": true, "self": 932.7515159869636, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0020783679997293802, "count": 1, "is_parallel": true, "self": 0.000665024999761954, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014133429999674263, "count": 8, "is_parallel": true, "self": 0.0014133429999674263 } } }, "UnityEnvironment.step": { "total": 0.050326257000051555, "count": 1, "is_parallel": true, "self": 0.0005306690004545089, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004982379996363306, "count": 1, "is_parallel": true, "self": 0.0004982379996363306 }, "communicator.exchange": { "total": 0.047714834999624145, "count": 1, "is_parallel": true, "self": 0.047714834999624145 }, "steps_from_proto": { "total": 0.0015825150003365707, "count": 1, "is_parallel": true, "self": 0.00034737000032691867, "children": { "_process_rank_one_or_two_observation": { "total": 0.001235145000009652, "count": 8, "is_parallel": true, "self": 0.001235145000009652 } } } } } } }, "UnityEnvironment.step": { "total": 1330.786021669027, "count": 64060, "is_parallel": true, "self": 31.6866859140614, "children": { "UnityEnvironment._generate_step_input": { "total": 23.53674646094578, "count": 64060, "is_parallel": true, "self": 23.53674646094578 }, "communicator.exchange": { "total": 1178.6292775270367, "count": 64060, "is_parallel": true, "self": 1178.6292775270367 }, "steps_from_proto": { "total": 96.93331176698302, "count": 64060, "is_parallel": true, "self": 19.333609221078405, "children": { "_process_rank_one_or_two_observation": { "total": 77.59970254590462, "count": 512480, "is_parallel": true, "self": 77.59970254590462 } } } } } } } } } } }, "trainer_advance": { "total": 668.639138734135, "count": 64061, "self": 2.6484782451971114, "children": { "process_trajectory": { "total": 129.4507896049372, "count": 64061, "self": 129.1384000429366, "children": { "RLTrainer._checkpoint": { "total": 0.31238956200058965, "count": 2, "self": 0.31238956200058965 } } }, "_update_policy": { "total": 536.5398708840007, "count": 461, "self": 294.53245716201127, "children": { "TorchPPOOptimizer.update": { "total": 242.00741372198945, "count": 22779, "self": 242.00741372198945 } } } } } } }, "trainer_threads": { "total": 1.0309995559509844e-06, "count": 1, "self": 1.0309995559509844e-06 }, "TrainerController._save_models": { "total": 0.10295541699997557, "count": 1, "self": 0.0019328200005475082, "children": { "RLTrainer._checkpoint": { "total": 0.10102259699942806, "count": 1, "self": 0.10102259699942806 } } } } } } }