{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.2923663556575775, "min": 0.2834899127483368, "max": 1.4814308881759644, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 8813.091796875, "min": 8554.591796875, "max": 44940.6875, "count": 33 }, "Pyramids.Step.mean": { "value": 989919.0, "min": 29883.0, "max": 989919.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989919.0, "min": 29883.0, "max": 989919.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6160231828689575, "min": -0.09294305741786957, "max": 0.6599060297012329, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 173.71853637695312, "min": -22.306333541870117, "max": 190.0529327392578, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.0065132249146699905, "min": -0.03305969014763832, "max": 0.6204302310943604, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -1.8367294073104858, "min": -8.562459945678711, "max": 147.04196166992188, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07093926178987162, "min": 0.06441282885498366, "max": 0.0746517829439602, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9931496650582027, "min": 0.4906396429402682, "max": 1.052681184649997, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01754030836067007, "min": 0.001487942634720087, "max": 0.017723943097282834, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.245564317049381, "min": 0.017855311616641042, "max": 0.24813520336195966, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.284354714771433e-06, "min": 7.284354714771433e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010198096600680006, "min": 0.00010198096600680006, "max": 0.0036333562888812994, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10242808571428574, "min": 0.10242808571428574, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4339932000000004, "min": 1.3886848, "max": 2.6175473000000005, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002525657628571431, "min": 0.0002525657628571431, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003535920680000003, "min": 0.003535920680000003, "max": 0.12113075813, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.011109928600490093, "min": 0.010771769098937511, "max": 0.4302145838737488, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.15553900599479675, "min": 0.15342684090137482, "max": 3.0115020275115967, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 302.88659793814435, "min": 293.375, "max": 988.8235294117648, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29380.0, "min": 16810.0, "max": 32271.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6761175083745385, "min": -0.8721176964395186, "max": 1.6818775372693733, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 162.58339831233025, "min": -28.244601652026176, "max": 171.48779846727848, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6761175083745385, "min": -0.8721176964395186, "max": 1.6818775372693733, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 162.58339831233025, "min": -28.244601652026176, "max": 171.48779846727848, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03501465330506464, "min": 0.03463666798030097, "max": 8.356590861783308, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.39642137059127, "min": 3.39336564776022, "max": 142.06204465031624, "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": "1714926125", "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": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1714928695" }, "total": 2569.6489016729997, "count": 1, "self": 0.8442853189999369, "children": { "run_training.setup": { "total": 0.055914451999797166, "count": 1, "self": 0.055914451999797166 }, "TrainerController.start_learning": { "total": 2568.748701902, "count": 1, "self": 1.8087172799409927, "children": { "TrainerController._reset_env": { "total": 2.239052851999986, "count": 1, "self": 2.239052851999986 }, "TrainerController.advance": { "total": 2564.5603547730584, "count": 64191, "self": 1.843451656203797, "children": { "env_step": { "total": 1896.435106992907, "count": 64191, "self": 1740.5715295749465, "children": { "SubprocessEnvManager._take_step": { "total": 154.73095599399812, "count": 64191, "self": 5.435737567005617, "children": { "TorchPolicy.evaluate": { "total": 149.2952184269925, "count": 62541, "self": 149.2952184269925 } } }, "workers": { "total": 1.1326214239625187, "count": 64191, "self": 0.0, "children": { "worker_root": { "total": 2562.196597381954, "count": 64191, "is_parallel": true, "self": 968.6471166708939, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0023482110000259127, "count": 1, "is_parallel": true, "self": 0.0007503579990952858, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015978530009306269, "count": 8, "is_parallel": true, "self": 0.0015978530009306269 } } }, "UnityEnvironment.step": { "total": 0.04956352199997127, "count": 1, "is_parallel": true, "self": 0.0006702890004817164, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00046813699964332045, "count": 1, "is_parallel": true, "self": 0.00046813699964332045 }, "communicator.exchange": { "total": 0.046643754999877274, "count": 1, "is_parallel": true, "self": 0.046643754999877274 }, "steps_from_proto": { "total": 0.0017813409999689611, "count": 1, "is_parallel": true, "self": 0.0003608120000535564, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014205289999154047, "count": 8, "is_parallel": true, "self": 0.0014205289999154047 } } } } } } }, "UnityEnvironment.step": { "total": 1593.54948071106, "count": 64190, "is_parallel": true, "self": 39.651053821123696, "children": { "UnityEnvironment._generate_step_input": { "total": 26.834509752856775, "count": 64190, "is_parallel": true, "self": 26.834509752856775 }, "communicator.exchange": { "total": 1409.970152737178, "count": 64190, "is_parallel": true, "self": 1409.970152737178 }, "steps_from_proto": { "total": 117.09376439990137, "count": 64190, "is_parallel": true, "self": 24.869085522346268, "children": { "_process_rank_one_or_two_observation": { "total": 92.2246788775551, "count": 513520, "is_parallel": true, "self": 92.2246788775551 } } } } } } } } } } }, "trainer_advance": { "total": 666.2817961239475, "count": 64191, "self": 3.2753944129253796, "children": { "process_trajectory": { "total": 143.00765095202496, "count": 64191, "self": 142.71255272102508, "children": { "RLTrainer._checkpoint": { "total": 0.2950982309998835, "count": 2, "self": 0.2950982309998835 } } }, "_update_policy": { "total": 519.9987507589972, "count": 453, "self": 306.90043542895046, "children": { "TorchPPOOptimizer.update": { "total": 213.09831533004672, "count": 22770, "self": 213.09831533004672 } } } } } } }, "trainer_threads": { "total": 1.42800035973778e-06, "count": 1, "self": 1.42800035973778e-06 }, "TrainerController._save_models": { "total": 0.14057556900024792, "count": 1, "self": 0.002161997000257543, "children": { "RLTrainer._checkpoint": { "total": 0.13841357199999038, "count": 1, "self": 0.13841357199999038 } } } } } } }