{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3716318607330322, "min": 0.3716318607330322, "max": 1.3881765604019165, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 11119.2255859375, "min": 11119.2255859375, "max": 42111.72265625, "count": 33 }, "Pyramids.Step.mean": { "value": 989948.0, "min": 29952.0, "max": 989948.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989948.0, "min": 29952.0, "max": 989948.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5520221590995789, "min": -0.0807473361492157, "max": 0.6285156011581421, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 155.6702423095703, "min": -19.540855407714844, "max": 180.38397216796875, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.006029200274497271, "min": -0.012511473149061203, "max": 0.5308569073677063, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 1.7002344131469727, "min": -3.353074789047241, "max": 127.93650817871094, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06681013170080925, "min": 0.06439228096217513, "max": 0.07316651910410396, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9353418438113295, "min": 0.5069407713920648, "max": 1.0781885947365606, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01794653715755668, "min": 0.0007959364282679759, "max": 0.01794653715755668, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.25125152020579355, "min": 0.00955123713921571, "max": 0.2575851337908306, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.678533154807148e-06, "min": 7.678533154807148e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010749946416730006, "min": 0.00010749946416730006, "max": 0.0036335446888185, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10255947857142855, "min": 0.10255947857142855, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4358326999999997, "min": 1.3886848, "max": 2.6111814999999994, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026569190928571446, "min": 0.00026569190928571446, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003719686730000002, "min": 0.003719686730000002, "max": 0.12113703185, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.015160898678004742, "min": 0.015160898678004742, "max": 0.6804297566413879, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.21225258708000183, "min": 0.21225258708000183, "max": 4.763008117675781, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 317.34375, "min": 310.6979166666667, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30465.0, "min": 15984.0, "max": 33097.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5784458133857697, "min": -1.0000000521540642, "max": 1.6893020641679566, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 151.5307980850339, "min": -29.772801652550697, "max": 162.17299816012383, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5784458133857697, "min": -1.0000000521540642, "max": 1.6893020641679566, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 151.5307980850339, "min": -29.772801652550697, "max": 162.17299816012383, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.049571789770804266, "min": 0.049571789770804266, "max": 13.399051713757217, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.75889181799721, "min": 4.75889181799721, "max": 214.38482742011547, "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": "1679513816", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[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": "1679516006" }, "total": 2190.490558073, "count": 1, "self": 0.48490632099947106, "children": { "run_training.setup": { "total": 0.17927686699999867, "count": 1, "self": 0.17927686699999867 }, "TrainerController.start_learning": { "total": 2189.8263748850004, "count": 1, "self": 1.5164754499974151, "children": { "TrainerController._reset_env": { "total": 6.109026415000017, "count": 1, "self": 6.109026415000017 }, "TrainerController.advance": { "total": 2182.1061725660024, "count": 63965, "self": 1.582868108011553, "children": { "env_step": { "total": 1555.813771851005, "count": 63965, "self": 1439.362561247073, "children": { "SubprocessEnvManager._take_step": { "total": 115.55060325494514, "count": 63965, "self": 4.801321585867299, "children": { "TorchPolicy.evaluate": { "total": 110.74928166907785, "count": 62548, "self": 110.74928166907785 } } }, "workers": { "total": 0.9006073489867958, "count": 63965, "self": 0.0, "children": { "worker_root": { "total": 2184.6190477709947, "count": 63965, "is_parallel": true, "self": 867.2697527770965, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018023000000084721, "count": 1, "is_parallel": true, "self": 0.0005373500002860965, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012649499997223757, "count": 8, "is_parallel": true, "self": 0.0012649499997223757 } } }, "UnityEnvironment.step": { "total": 0.04486401300005127, "count": 1, "is_parallel": true, "self": 0.0005117719999816472, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00048426800003653625, "count": 1, "is_parallel": true, "self": 0.00048426800003653625 }, "communicator.exchange": { "total": 0.04228749699996115, "count": 1, "is_parallel": true, "self": 0.04228749699996115 }, "steps_from_proto": { "total": 0.0015804760000719398, "count": 1, "is_parallel": true, "self": 0.00034896300053333107, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012315129995386087, "count": 8, "is_parallel": true, "self": 0.0012315129995386087 } } } } } } }, "UnityEnvironment.step": { "total": 1317.3492949938982, "count": 63964, "is_parallel": true, "self": 31.81441099199469, "children": { "UnityEnvironment._generate_step_input": { "total": 22.87449696990916, "count": 63964, "is_parallel": true, "self": 22.87449696990916 }, "communicator.exchange": { "total": 1168.9190391709853, "count": 63964, "is_parallel": true, "self": 1168.9190391709853 }, "steps_from_proto": { "total": 93.74134786100899, "count": 63964, "is_parallel": true, "self": 20.54246162596428, "children": { "_process_rank_one_or_two_observation": { "total": 73.19888623504471, "count": 511712, "is_parallel": true, "self": 73.19888623504471 } } } } } } } } } } }, "trainer_advance": { "total": 624.7095326069859, "count": 63965, "self": 2.959575394979538, "children": { "process_trajectory": { "total": 119.7156706589999, "count": 63965, "self": 119.51752013500027, "children": { "RLTrainer._checkpoint": { "total": 0.1981505239996295, "count": 2, "self": 0.1981505239996295 } } }, "_update_policy": { "total": 502.0342865530065, "count": 456, "self": 316.3847812570316, "children": { "TorchPPOOptimizer.update": { "total": 185.6495052959749, "count": 22821, "self": 185.6495052959749 } } } } } } }, "trainer_threads": { "total": 1.0630001270328648e-06, "count": 1, "self": 1.0630001270328648e-06 }, "TrainerController._save_models": { "total": 0.09469939100017655, "count": 1, "self": 0.001404193000325904, "children": { "RLTrainer._checkpoint": { "total": 0.09329519799985064, "count": 1, "self": 0.09329519799985064 } } } } } } }