{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.1466219127178192, "min": 0.1376461386680603, "max": 1.452722430229187, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 4398.6572265625, "min": 4098.55126953125, "max": 44069.7890625, "count": 100 }, "Pyramids.Step.mean": { "value": 2999928.0, "min": 29952.0, "max": 2999928.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999928.0, "min": 29952.0, "max": 2999928.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.8670655488967896, "min": -0.1046089231967926, "max": 0.9217798709869385, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 262.7208557128906, "min": -25.210750579833984, "max": 290.36065673828125, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.003384210867807269, "min": -0.015324176289141178, "max": 0.382351815700531, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -1.0254158973693848, "min": -4.5666046142578125, "max": 90.61737823486328, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06604054847581206, "min": 0.06344112334495765, "max": 0.07383879040243499, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9245676786613689, "min": 0.5047615552301005, "max": 1.0925224991629412, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015259490603852054, "min": 0.00035080819639906485, "max": 0.016221476886823356, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21363286845392876, "min": 0.004911314749586908, "max": 0.2286844938935246, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.4642923690785687e-06, "min": 1.4642923690785687e-06, "max": 0.00029838354339596195, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.050009316709996e-05, "min": 2.050009316709996e-05, "max": 0.0039278379907207, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10048806428571429, "min": 0.10048806428571429, "max": 0.19946118095238097, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4068329, "min": 1.3962282666666668, "max": 2.7374854000000006, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 5.875762214285705e-05, "min": 5.875762214285705e-05, "max": 0.009946171977142856, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.0008226067099999987, "min": 0.0008226067099999987, "max": 0.13093700207, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.008717983029782772, "min": 0.00863488856703043, "max": 0.6031671762466431, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.12205176800489426, "min": 0.12205176800489426, "max": 4.222170352935791, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 213.12230215827338, "min": 194.3741935483871, "max": 999.0, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29624.0, "min": 15984.0, "max": 33402.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7868776863856282, "min": -1.0000000521540642, "max": 1.8056257942030507, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 248.3759984076023, "min": -30.50000174343586, "max": 279.87199810147285, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7868776863856282, "min": -1.0000000521540642, "max": 1.8056257942030507, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 248.3759984076023, "min": -30.50000174343586, "max": 279.87199810147285, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.019461033346232785, "min": 0.01832524779658284, "max": 12.011840673163533, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 2.705083635126357, "min": 2.632577312300782, "max": 192.18945077061653, "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": "1683516823", "python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [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": "1683528909" }, "total": 12086.856356602, "count": 1, "self": 0.7530177350017766, "children": { "run_training.setup": { "total": 0.0537485470001684, "count": 1, "self": 0.0537485470001684 }, "TrainerController.start_learning": { "total": 12086.049590319999, "count": 1, "self": 7.820710280759158, "children": { "TrainerController._reset_env": { "total": 1.329903646000048, "count": 1, "self": 1.329903646000048 }, "TrainerController.advance": { "total": 12076.77186443324, "count": 194808, "self": 7.816435076923881, "children": { "env_step": { "total": 8307.594732475147, "count": 194808, "self": 7856.158219697929, "children": { "SubprocessEnvManager._take_step": { "total": 446.9094279560411, "count": 194808, "self": 23.38428826201448, "children": { "TorchPolicy.evaluate": { "total": 423.5251396940266, "count": 187563, "self": 423.5251396940266 } } }, "workers": { "total": 4.527084821177368, "count": 194808, "self": 0.0, "children": { "worker_root": { "total": 12061.864726641637, "count": 194808, "is_parallel": true, "self": 4771.098605724532, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002286290000029112, "count": 1, "is_parallel": true, "self": 0.0006734060002600017, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016128839997691102, "count": 8, "is_parallel": true, "self": 0.0016128839997691102 } } }, "UnityEnvironment.step": { "total": 0.06684882100012146, "count": 1, "is_parallel": true, "self": 0.000683477999700699, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005737380001846759, "count": 1, "is_parallel": true, "self": 0.0005737380001846759 }, "communicator.exchange": { "total": 0.06332381900006112, "count": 1, "is_parallel": true, "self": 0.06332381900006112 }, "steps_from_proto": { "total": 0.002267786000174965, "count": 1, "is_parallel": true, "self": 0.00043407700013631256, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018337090000386524, "count": 8, "is_parallel": true, "self": 0.0018337090000386524 } } } } } } }, "UnityEnvironment.step": { "total": 7290.766120917106, "count": 194807, "is_parallel": true, "self": 143.6200553835506, "children": { "UnityEnvironment._generate_step_input": { "total": 89.05001901207402, "count": 194807, "is_parallel": true, "self": 89.05001901207402 }, "communicator.exchange": { "total": 6614.860447815136, "count": 194807, "is_parallel": true, "self": 6614.860447815136 }, "steps_from_proto": { "total": 443.2355987063454, "count": 194807, "is_parallel": true, "self": 96.39494141992054, "children": { "_process_rank_one_or_two_observation": { "total": 346.84065728642486, "count": 1558456, "is_parallel": true, "self": 346.84065728642486 } } } } } } } } } } }, "trainer_advance": { "total": 3761.360696881169, "count": 194808, "self": 14.49782779105226, "children": { "process_trajectory": { "total": 475.3756091831301, "count": 194808, "self": 474.43710613512803, "children": { "RLTrainer._checkpoint": { "total": 0.938503048002076, "count": 6, "self": 0.938503048002076 } } }, "_update_policy": { "total": 3271.4872599069868, "count": 1391, "self": 1342.7079113280533, "children": { "TorchPPOOptimizer.update": { "total": 1928.7793485789334, "count": 68391, "self": 1928.7793485789334 } } } } } } }, "trainer_threads": { "total": 1.3730004866374657e-06, "count": 1, "self": 1.3730004866374657e-06 }, "TrainerController._save_models": { "total": 0.12711058700006106, "count": 1, "self": 0.0023170740005298285, "children": { "RLTrainer._checkpoint": { "total": 0.12479351299953123, "count": 1, "self": 0.12479351299953123 } } } } } } }