{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.16888731718063354, "min": 0.16335463523864746, "max": 1.3342252969741821, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 5055.810546875, "min": 4858.8203125, "max": 40475.05859375, "count": 100 }, "Pyramids.Step.mean": { "value": 2999960.0, "min": 29880.0, "max": 2999960.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999960.0, "min": 29880.0, "max": 2999960.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.8323410153388977, "min": -0.09936357289552689, "max": 0.8599370121955872, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 250.53463745117188, "min": -23.94662094116211, "max": 262.5152587890625, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.0007592196925543249, "min": -0.019779907539486885, "max": 0.4906107187271118, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -0.22852513194084167, "min": -6.072431564331055, "max": 116.76535034179688, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06739557392263253, "min": 0.061611131543112506, "max": 0.07381829316450639, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9435380349168553, "min": 0.6564119241704127, "max": 1.0887954444670136, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01564988448600551, "min": 4.475361368075403e-05, "max": 0.01782436991240555, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21909838280407715, "min": 0.0006265505915305564, "max": 0.2495411787736777, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.5819780441357146e-06, "min": 1.5819780441357146e-06, "max": 0.00029826981168784073, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.2147692617900004e-05, "min": 2.2147692617900004e-05, "max": 0.0040109925630024985, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10052729285714287, "min": 0.10052729285714287, "max": 0.1994232703703704, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4073821000000002, "min": 1.4073821000000002, "max": 2.7975608333333333, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 6.267655642857145e-05, "min": 6.267655642857145e-05, "max": 0.00994238471, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.0008774717900000003, "min": 0.0008774717900000003, "max": 0.13370605024999999, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.00796900037676096, "min": 0.00779154384508729, "max": 0.6174203753471375, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.11156600713729858, "min": 0.10908161103725433, "max": 5.556783199310303, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 215.1865671641791, "min": 199.92307692307693, "max": 995.5862068965517, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28835.0, "min": 16679.0, "max": 32160.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7847238662305163, "min": -0.9287548882346, "max": 1.8000769110826345, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 239.15299807488918, "min": -29.598001658916473, "max": 257.41099828481674, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7847238662305163, "min": -0.9287548882346, "max": 1.8000769110826345, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 239.15299807488918, "min": -29.598001658916473, "max": 257.41099828481674, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.017905389509987393, "min": 0.017307968961011447, "max": 12.270657558651532, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 2.3993221943383105, "min": 2.336041350274172, "max": 208.60117849707603, "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": "1678440162", "python_version": "3.8.16 (default, Mar 2 2023, 03:21:46) \n[GCC 11.2.0]", "command_line_arguments": "/home/ikari/miniconda3/envs/unity/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics", "mlagents_version": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.23.5", "end_time_seconds": "1678456039" }, "total": 15876.950356653892, "count": 1, "self": 0.32106239162385464, "children": { "run_training.setup": { "total": 0.011915852315723896, "count": 1, "self": 0.011915852315723896 }, "TrainerController.start_learning": { "total": 15876.617378409952, "count": 1, "self": 3.4065142404288054, "children": { "TrainerController._reset_env": { "total": 2.904724134132266, "count": 1, "self": 2.904724134132266 }, "TrainerController.advance": { "total": 15870.200008274987, "count": 195274, "self": 3.091154070571065, "children": { "env_step": { "total": 14319.79124906566, "count": 195274, "self": 14095.995129442774, "children": { "SubprocessEnvManager._take_step": { "total": 221.72945375274867, "count": 195274, "self": 9.289458124898374, "children": { "TorchPolicy.evaluate": { "total": 212.4399956278503, "count": 187567, "self": 72.42416426260024, "children": { "TorchPolicy.sample_actions": { "total": 140.01583136525005, "count": 187567, "self": 140.01583136525005 } } } } }, "workers": { "total": 2.0666658701375127, "count": 195274, "self": 0.0, "children": { "worker_root": { "total": 15870.175473171286, "count": 195274, "is_parallel": true, "self": 2045.5323042850941, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002430250868201256, "count": 1, "is_parallel": true, "self": 0.0007194317877292633, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017108190804719925, "count": 8, "is_parallel": true, "self": 0.0017108190804719925 } } }, "UnityEnvironment.step": { "total": 0.10187257546931505, "count": 1, "is_parallel": true, "self": 0.0002037622034549713, "children": { "UnityEnvironment._generate_step_input": { "total": 0.002173912711441517, "count": 1, "is_parallel": true, "self": 0.002173912711441517 }, "communicator.exchange": { "total": 0.09760181047022343, "count": 1, "is_parallel": true, "self": 0.09760181047022343 }, "steps_from_proto": { "total": 0.001893090084195137, "count": 1, "is_parallel": true, "self": 0.0004205619916319847, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014725280925631523, "count": 8, "is_parallel": true, "self": 0.0014725280925631523 } } } } } } }, "UnityEnvironment.step": { "total": 13824.643168886192, "count": 195273, "is_parallel": true, "self": 34.007187825627625, "children": { "UnityEnvironment._generate_step_input": { "total": 195.40542417671531, "count": 195273, "is_parallel": true, "self": 195.40542417671531 }, "communicator.exchange": { "total": 13311.706894907169, "count": 195273, "is_parallel": true, "self": 13311.706894907169 }, "steps_from_proto": { "total": 283.52366197668016, "count": 195273, "is_parallel": true, "self": 59.69808935932815, "children": { "_process_rank_one_or_two_observation": { "total": 223.825572617352, "count": 1562184, "is_parallel": true, "self": 223.825572617352 } } } } } } } } } } }, "trainer_advance": { "total": 1547.3176051387563, "count": 195274, "self": 6.971099619753659, "children": { "process_trajectory": { "total": 309.376894203946, "count": 195274, "self": 308.8838390754536, "children": { "RLTrainer._checkpoint": { "total": 0.49305512849241495, "count": 6, "self": 0.49305512849241495 } } }, "_update_policy": { "total": 1230.9696113150567, "count": 1404, "self": 315.81197070516646, "children": { "TorchPPOOptimizer.update": { "total": 915.1576406098902, "count": 68352, "self": 915.1576406098902 } } } } } } }, "trainer_threads": { "total": 6.379559636116028e-07, "count": 1, "self": 6.379559636116028e-07 }, "TrainerController._save_models": { "total": 0.1061311224475503, "count": 1, "self": 0.0009916843846440315, "children": { "RLTrainer._checkpoint": { "total": 0.10513943806290627, "count": 1, "self": 0.10513943806290627 } } } } } } }