{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3077658414840698, "min": 0.3077658414840698, "max": 1.4557534456253052, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 9124.6416015625, "min": 9124.6416015625, "max": 44161.73828125, "count": 33 }, "Pyramids.Step.mean": { "value": 989990.0, "min": 29952.0, "max": 989990.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989990.0, "min": 29952.0, "max": 989990.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6076011061668396, "min": -0.10638713091611862, "max": 0.6076011061668396, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 171.95111083984375, "min": -25.745685577392578, "max": 171.95111083984375, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.023528097197413445, "min": 0.0032839360646903515, "max": 0.2947067618370056, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 6.658451557159424, "min": 0.8997985124588013, "max": 70.37000274658203, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06572233069457697, "min": 0.06572233069457697, "max": 0.07632994608613473, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9201126297240776, "min": 0.48759347025201993, "max": 1.1128420425617758, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014950553591233345, "min": 0.00024810997997757873, "max": 0.015618829387625715, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.20930775027726684, "min": 0.002977319759730945, "max": 0.21866361142676002, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 2.2326204662178568e-05, "min": 2.2326204662178568e-05, "max": 0.0008854518873307427, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00031256686527049996, "min": 0.00031256686527049996, "max": 0.010902717188587, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10248067857142858, "min": 0.10248067857142858, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4347295, "min": 1.3886848, "max": 2.6114129999999998, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002578197892857143, "min": 0.0002578197892857143, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036094770500000005, "min": 0.0036094770500000005, "max": 0.12116015870000002, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.011100380681455135, "min": 0.010823632590472698, "max": 0.3624297082424164, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.15540532767772675, "min": 0.15153086185455322, "max": 2.537008047103882, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 331.8888888888889, "min": 316.06451612903226, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29870.0, "min": 15984.0, "max": 32690.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.601424430973, "min": -1.0000000521540642, "max": 1.601424430973, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 144.12819878757, "min": -31.997201651334763, "max": 146.6027987897396, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.601424430973, "min": -1.0000000521540642, "max": 1.601424430973, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 144.12819878757, "min": -31.997201651334763, "max": 146.6027987897396, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03795206053853488, "min": 0.03645109418185487, "max": 6.6690348740667105, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.415685448468139, "min": 3.279232022468932, "max": 106.70455798506737, "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": "1767985783", "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 --force", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1767987838" }, "total": 2055.325285949999, "count": 1, "self": 0.48913402700054576, "children": { "run_training.setup": { "total": 0.024919464998674812, "count": 1, "self": 0.024919464998674812 }, "TrainerController.start_learning": { "total": 2054.8112324579997, "count": 1, "self": 1.1566148190759122, "children": { "TrainerController._reset_env": { "total": 2.108845319999091, "count": 1, "self": 2.108845319999091 }, "TrainerController.advance": { "total": 2051.4727714569253, "count": 63985, "self": 1.2100021909336647, "children": { "env_step": { "total": 1424.3113001127367, "count": 63985, "self": 1289.0263275186917, "children": { "SubprocessEnvManager._take_step": { "total": 134.58709203713443, "count": 63985, "self": 4.276102659037861, "children": { "TorchPolicy.evaluate": { "total": 130.31098937809656, "count": 62564, "self": 130.31098937809656 } } }, "workers": { "total": 0.6978805569106044, "count": 63985, "self": 0.0, "children": { "worker_root": { "total": 2048.001219860991, "count": 63985, "is_parallel": true, "self": 865.7896409550158, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018659720008145086, "count": 1, "is_parallel": true, "self": 0.0006148520023998572, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012511199984146515, "count": 8, "is_parallel": true, "self": 0.0012511199984146515 } } }, "UnityEnvironment.step": { "total": 0.04624707299990405, "count": 1, "is_parallel": true, "self": 0.0005119610013935016, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004394829993543681, "count": 1, "is_parallel": true, "self": 0.0004394829993543681 }, "communicator.exchange": { "total": 0.04368594399966241, "count": 1, "is_parallel": true, "self": 0.04368594399966241 }, "steps_from_proto": { "total": 0.0016096849994937656, "count": 1, "is_parallel": true, "self": 0.0003349349990457995, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012747500004479662, "count": 8, "is_parallel": true, "self": 0.0012747500004479662 } } } } } } }, "UnityEnvironment.step": { "total": 1182.2115789059753, "count": 63984, "is_parallel": true, "self": 32.18256358663348, "children": { "UnityEnvironment._generate_step_input": { "total": 21.67378137320884, "count": 63984, "is_parallel": true, "self": 21.67378137320884 }, "communicator.exchange": { "total": 1029.7186597791315, "count": 63984, "is_parallel": true, "self": 1029.7186597791315 }, "steps_from_proto": { "total": 98.63657416700153, "count": 63984, "is_parallel": true, "self": 20.015053971887028, "children": { "_process_rank_one_or_two_observation": { "total": 78.6215201951145, "count": 511872, "is_parallel": true, "self": 78.6215201951145 } } } } } } } } } } }, "trainer_advance": { "total": 625.951469153255, "count": 63985, "self": 2.3741316305222426, "children": { "process_trajectory": { "total": 117.47345009472338, "count": 63985, "self": 117.28902259672213, "children": { "RLTrainer._checkpoint": { "total": 0.18442749800124147, "count": 2, "self": 0.18442749800124147 } } }, "_update_policy": { "total": 506.10388742800933, "count": 455, "self": 280.3175839379928, "children": { "TorchPPOOptimizer.update": { "total": 225.7863034900165, "count": 22800, "self": 225.7863034900165 } } } } } } }, "trainer_threads": { "total": 8.139995770761743e-07, "count": 1, "self": 8.139995770761743e-07 }, "TrainerController._save_models": { "total": 0.07300004799981252, "count": 1, "self": 0.001346347000435344, "children": { "RLTrainer._checkpoint": { "total": 0.07165370099937718, "count": 1, "self": 0.07165370099937718 } } } } } } }