{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.36912745237350464, "min": 0.36051255464553833, "max": 1.3815783262252808, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 11056.10546875, "min": 10931.5673828125, "max": 41911.55859375, "count": 33 }, "Pyramids.Step.mean": { "value": 989967.0, "min": 29952.0, "max": 989967.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989967.0, "min": 29952.0, "max": 989967.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5876592397689819, "min": -0.1077943667769432, "max": 0.7014960646629333, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 164.54458618164062, "min": -25.618764877319336, "max": 204.83685302734375, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.014482378959655762, "min": 0.0047548552975058556, "max": 0.46964848041534424, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 4.055066108703613, "min": 1.3884177207946777, "max": 111.30668640136719, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06923854927992493, "min": 0.0645831366056082, "max": 0.07307940500203255, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.969339689918949, "min": 0.5115558350142279, "max": 1.0537786235508975, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015228316571059013, "min": 0.00029393436593660587, "max": 0.017557169614789855, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21319643199482619, "min": 0.00352721239123927, "max": 0.24580037460705798, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.369833257707146e-06, "min": 7.369833257707146e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010317766560790005, "min": 0.00010317766560790005, "max": 0.0035080178306607993, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10245657857142856, "min": 0.10245657857142856, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4343921, "min": 1.3886848, "max": 2.5693392000000004, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025541219928571445, "min": 0.00025541219928571445, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035757707900000023, "min": 0.0035757707900000023, "max": 0.11695698608, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01120752189308405, "min": 0.01120752189308405, "max": 0.6749972105026245, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.15690530836582184, "min": 0.15690530836582184, "max": 4.724980354309082, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 313.05555555555554, "min": 266.0450450450451, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28175.0, "min": 15984.0, "max": 34278.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6647110855413807, "min": -1.0000000521540642, "max": 1.7339549335810516, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 149.82399769872427, "min": -31.99640166759491, "max": 192.46899762749672, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6647110855413807, "min": -1.0000000521540642, "max": 1.7339549335810516, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 149.82399769872427, "min": -31.99640166759491, "max": 192.46899762749672, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.0362262910539155, "min": 0.03340298353604184, "max": 13.32140034623444, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.260366194852395, "min": 3.260366194852395, "max": 213.14240553975105, "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": "1678993515", "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": "1678995842" }, "total": 2327.4356937639996, "count": 1, "self": 0.8307916789990486, "children": { "run_training.setup": { "total": 0.10988056000019242, "count": 1, "self": 0.10988056000019242 }, "TrainerController.start_learning": { "total": 2326.495021525, "count": 1, "self": 1.5365523819700684, "children": { "TrainerController._reset_env": { "total": 6.401855099999921, "count": 1, "self": 6.401855099999921 }, "TrainerController.advance": { "total": 2318.3983481950304, "count": 64056, "self": 1.6391075849442132, "children": { "env_step": { "total": 1659.5497505490664, "count": 64056, "self": 1542.1294962631096, "children": { "SubprocessEnvManager._take_step": { "total": 116.51795856797753, "count": 64056, "self": 5.128729681949608, "children": { "TorchPolicy.evaluate": { "total": 111.38922888602792, "count": 62562, "self": 111.38922888602792 } } }, "workers": { "total": 0.9022957179793138, "count": 64056, "self": 0.0, "children": { "worker_root": { "total": 2320.676845064952, "count": 64056, "is_parallel": true, "self": 903.531500594934, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018883290001667774, "count": 1, "is_parallel": true, "self": 0.0006171810000523692, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012711480001144082, "count": 8, "is_parallel": true, "self": 0.0012711480001144082 } } }, "UnityEnvironment.step": { "total": 0.10476054900004783, "count": 1, "is_parallel": true, "self": 0.0005780170001798979, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00047090299995034, "count": 1, "is_parallel": true, "self": 0.00047090299995034 }, "communicator.exchange": { "total": 0.10178368399988358, "count": 1, "is_parallel": true, "self": 0.10178368399988358 }, "steps_from_proto": { "total": 0.0019279450000340148, "count": 1, "is_parallel": true, "self": 0.00040681799987396516, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015211270001600496, "count": 8, "is_parallel": true, "self": 0.0015211270001600496 } } } } } } }, "UnityEnvironment.step": { "total": 1417.145344470018, "count": 64055, "is_parallel": true, "self": 32.769134677049806, "children": { "UnityEnvironment._generate_step_input": { "total": 25.039868696981785, "count": 64055, "is_parallel": true, "self": 25.039868696981785 }, "communicator.exchange": { "total": 1257.526770057053, "count": 64055, "is_parallel": true, "self": 1257.526770057053 }, "steps_from_proto": { "total": 101.80957103893343, "count": 64055, "is_parallel": true, "self": 22.41798029295751, "children": { "_process_rank_one_or_two_observation": { "total": 79.39159074597592, "count": 512440, "is_parallel": true, "self": 79.39159074597592 } } } } } } } } } } }, "trainer_advance": { "total": 657.2094900610198, "count": 64056, "self": 2.714929414968765, "children": { "process_trajectory": { "total": 128.79451046105237, "count": 64056, "self": 128.53191010305204, "children": { "RLTrainer._checkpoint": { "total": 0.2626003580003271, "count": 2, "self": 0.2626003580003271 } } }, "_update_policy": { "total": 525.7000501849986, "count": 453, "self": 336.12933830199904, "children": { "TorchPPOOptimizer.update": { "total": 189.5707118829996, "count": 22818, "self": 189.5707118829996 } } } } } } }, "trainer_threads": { "total": 1.7339998521492817e-06, "count": 1, "self": 1.7339998521492817e-06 }, "TrainerController._save_models": { "total": 0.15826411399984863, "count": 1, "self": 0.0020372539997879358, "children": { "RLTrainer._checkpoint": { "total": 0.1562268600000607, "count": 1, "self": 0.1562268600000607 } } } } } } }