{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5098013877868652, "min": 0.5098013877868652, "max": 1.5134235620498657, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 15204.31640625, "min": 15204.31640625, "max": 45911.21875, "count": 33 }, "Pyramids.Step.mean": { "value": 989953.0, "min": 29952.0, "max": 989953.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989953.0, "min": 29952.0, "max": 989953.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.33902332186698914, "min": -0.11520419269800186, "max": 0.33902332186698914, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 87.468017578125, "min": -27.533802032470703, "max": 87.468017578125, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.1367684304714203, "min": -0.1367684304714203, "max": 0.3536145091056824, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -35.2862548828125, "min": -35.2862548828125, "max": 83.806640625, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06703367491510497, "min": 0.0632439712435855, "max": 0.07265968720145922, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9384714488114696, "min": 0.49478018794566037, "max": 1.0246493051755332, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01391560150191903, "min": 0.00015629068456560197, "max": 0.015484059234549872, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.19481842102686642, "min": 0.0020317788993528254, "max": 0.19481842102686642, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.385047538349998e-06, "min": 7.385047538349998e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010339066553689998, "min": 0.00010339066553689998, "max": 0.0033816620727794003, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10246165, "min": 0.10246165, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4344631, "min": 1.3886848, "max": 2.5272206000000006, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025591883499999997, "min": 0.00025591883499999997, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035828636899999998, "min": 0.0035828636899999998, "max": 0.11274933794000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.014161154627799988, "min": 0.014161154627799988, "max": 0.49880415201187134, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.19825616478919983, "min": 0.19825616478919983, "max": 3.491629123687744, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 536.5535714285714, "min": 493.9, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30047.0, "min": 15984.0, "max": 32945.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.1717527038671753, "min": -1.0000000521540642, "max": 1.2483626814969515, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 64.44639871269464, "min": -31.996001660823822, "max": 73.65339820832014, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.1717527038671753, "min": -1.0000000521540642, "max": 1.2483626814969515, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 64.44639871269464, "min": -31.996001660823822, "max": 73.65339820832014, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.07797861532519826, "min": 0.07547148235607892, "max": 10.972541344352067, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.288823842885904, "min": 4.288823842885904, "max": 175.56066150963306, "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": "1674558146", "python_version": "3.8.10 (default, Jun 22 2022, 20:18:18) \n[GCC 9.4.0]", "command_line_arguments": "/home/acl/Desktop/robot-learning/huggingface/5.ml-agents/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": "1.20.0", "end_time_seconds": "1674560148" }, "total": 2001.748282595, "count": 1, "self": 0.21796494900036123, "children": { "run_training.setup": { "total": 0.011570411999855423, "count": 1, "self": 0.011570411999855423 }, "TrainerController.start_learning": { "total": 2001.5187472339999, "count": 1, "self": 0.9144593958681071, "children": { "TrainerController._reset_env": { "total": 2.304729601999952, "count": 1, "self": 2.304729601999952 }, "TrainerController.advance": { "total": 1998.2486745491324, "count": 63370, "self": 0.9724202790844174, "children": { "env_step": { "total": 1630.4360189600147, "count": 63370, "self": 1555.0251097240593, "children": { "SubprocessEnvManager._take_step": { "total": 74.83801029493225, "count": 63370, "self": 2.554910472057145, "children": { "TorchPolicy.evaluate": { "total": 72.2830998228751, "count": 62566, "self": 26.471130609852935, "children": { "TorchPolicy.sample_actions": { "total": 45.81196921302217, "count": 62566, "self": 45.81196921302217 } } } } }, "workers": { "total": 0.5728989410231407, "count": 63370, "self": 0.0, "children": { "worker_root": { "total": 1999.7533224910144, "count": 63370, "is_parallel": true, "self": 510.1366617960339, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0010483480000402778, "count": 1, "is_parallel": true, "self": 0.00034898599960797583, "children": { "_process_rank_one_or_two_observation": { "total": 0.000699362000432302, "count": 8, "is_parallel": true, "self": 0.000699362000432302 } } }, "UnityEnvironment.step": { "total": 0.038456291000329657, "count": 1, "is_parallel": true, "self": 0.00010491400007595075, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000398452999888832, "count": 1, "is_parallel": true, "self": 0.000398452999888832 }, "communicator.exchange": { "total": 0.03734535400008099, "count": 1, "is_parallel": true, "self": 0.03734535400008099 }, "steps_from_proto": { "total": 0.0006075700002838857, "count": 1, "is_parallel": true, "self": 0.00016786600099294446, "children": { "_process_rank_one_or_two_observation": { "total": 0.0004397039992909413, "count": 8, "is_parallel": true, "self": 0.0004397039992909413 } } } } } } }, "UnityEnvironment.step": { "total": 1489.6166606949805, "count": 63369, "is_parallel": true, "self": 6.646683408926037, "children": { "UnityEnvironment._generate_step_input": { "total": 24.99322556692823, "count": 63369, "is_parallel": true, "self": 24.99322556692823 }, "communicator.exchange": { "total": 1419.4169564410804, "count": 63369, "is_parallel": true, "self": 1419.4169564410804 }, "steps_from_proto": { "total": 38.55979527804584, "count": 63369, "is_parallel": true, "self": 10.337993527875824, "children": { "_process_rank_one_or_two_observation": { "total": 28.221801750170016, "count": 506952, "is_parallel": true, "self": 28.221801750170016 } } } } } } } } } } }, "trainer_advance": { "total": 366.8402353100332, "count": 63370, "self": 1.764739047088824, "children": { "process_trajectory": { "total": 75.44809703794726, "count": 63370, "self": 75.34770481794749, "children": { "RLTrainer._checkpoint": { "total": 0.10039221999977599, "count": 2, "self": 0.10039221999977599 } } }, "_update_policy": { "total": 289.62739922499713, "count": 445, "self": 108.65385058195534, "children": { "TorchPPOOptimizer.update": { "total": 180.9735486430418, "count": 22809, "self": 180.9735486430418 } } } } } } }, "trainer_threads": { "total": 8.079996405285783e-07, "count": 1, "self": 8.079996405285783e-07 }, "TrainerController._save_models": { "total": 0.050882878999800596, "count": 1, "self": 0.0007754890002615866, "children": { "RLTrainer._checkpoint": { "total": 0.05010738999953901, "count": 1, "self": 0.05010738999953901 } } } } } } }