{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.9092274308204651, "min": 0.9092274308204651, "max": 1.4284991025924683, "count": 3 }, "Pyramids.Policy.Entropy.sum": { "value": 27742.34765625, "min": 27742.34765625, "max": 43334.94921875, "count": 3 }, "Pyramids.Step.mean": { "value": 89958.0, "min": 29952.0, "max": 89958.0, "count": 3 }, "Pyramids.Step.sum": { "value": 89958.0, "min": 29952.0, "max": 89958.0, "count": 3 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": -0.08864111453294754, "min": -0.12836232781410217, "max": -0.08864111453294754, "count": 3 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": -21.539791107177734, "min": -30.421871185302734, "max": -21.539791107177734, "count": 3 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.2048972100019455, "min": 0.2048972100019455, "max": 0.5543301701545715, "count": 3 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 49.79002380371094, "min": 49.79002380371094, "max": 131.37625122070312, "count": 3 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06787982789588877, "min": 0.06787982789588877, "max": 0.07495863438083626, "count": 3 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.8145579347506652, "min": 0.48445051893874225, "max": 0.8145579347506652, "count": 3 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.0019506415660516835, "min": 0.0019506415660516835, "max": 0.010849039566596618, "count": 3 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.023407698792620203, "min": 0.0197879623809503, "max": 0.07594327696617632, "count": 3 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.621157459616666e-05, "min": 7.621157459616666e-05, "max": 0.0002515063018788571, "count": 3 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0009145388951539999, "min": 0.0009145388951539999, "max": 0.0017605441131519997, "count": 3 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.12540383333333335, "min": 0.12540383333333335, "max": 0.1838354285714286, "count": 3 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5048460000000001, "min": 1.2868480000000002, "max": 1.5048460000000001, "count": 3 }, "Pyramids.Policy.Beta.mean": { "value": 0.00254784295, "min": 0.00254784295, "max": 0.008385159314285713, "count": 3 }, "Pyramids.Policy.Beta.sum": { "value": 0.030574115399999997, "min": 0.030574115399999997, "max": 0.058696115199999996, "count": 3 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.13332273066043854, "min": 0.13332273066043854, "max": 0.5479043126106262, "count": 3 }, "Pyramids.Losses.RNDLoss.sum": { "value": 1.5998728275299072, "min": 1.5998728275299072, "max": 3.835330009460449, "count": 3 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 976.6363636363636, "min": 976.6363636363636, "max": 999.0, "count": 3 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 32229.0, "min": 15984.0, "max": 32229.0, "count": 3 }, "Pyramids.Environment.CumulativeReward.mean": { "value": -0.7956485335122455, "min": -1.0000000521540642, "max": -0.7956485335122455, "count": 3 }, "Pyramids.Environment.CumulativeReward.sum": { "value": -26.256401605904102, "min": -27.71000164747238, "max": -16.000000834465027, "count": 3 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": -0.7956485335122455, "min": -1.0000000521540642, "max": -0.7956485335122455, "count": 3 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": -26.256401605904102, "min": -27.71000164747238, "max": -16.000000834465027, "count": 3 }, "Pyramids.Policy.RndReward.mean": { "value": 1.4937772295353087, "min": 1.4937772295353087, "max": 12.03578020259738, "count": 3 }, "Pyramids.Policy.RndReward.sum": { "value": 49.29464857466519, "min": 49.29464857466519, "max": 192.57248324155807, "count": 3 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 3 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 3 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1667572062", "python_version": "3.7.15 (default, Oct 12 2022, 19:14:55) \n[GCC 7.5.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./trained-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics --force", "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": "1.21.6", "end_time_seconds": "1667572256" }, "total": 194.01139084499982, "count": 1, "self": 0.4283941269998195, "children": { "run_training.setup": { "total": 0.04214013299997532, "count": 1, "self": 0.04214013299997532 }, "TrainerController.start_learning": { "total": 193.54085658500003, "count": 1, "self": 0.12800698199134786, "children": { "TrainerController._reset_env": { "total": 6.460049034999884, "count": 1, "self": 6.460049034999884 }, "TrainerController.advance": { "total": 186.84631138100872, "count": 6310, "self": 0.14312978500333884, "children": { "env_step": { "total": 114.29843262700865, "count": 6310, "self": 103.27761538800837, "children": { "SubprocessEnvManager._take_step": { "total": 10.95142740700112, "count": 6310, "self": 0.45551928700683675, "children": { "TorchPolicy.evaluate": { "total": 10.495908119994283, "count": 6298, "self": 3.538826021985642, "children": { "TorchPolicy.sample_actions": { "total": 6.957082098008641, "count": 6298, "self": 6.957082098008641 } } } } }, "workers": { "total": 0.06938983199916038, "count": 6310, "self": 0.0, "children": { "worker_root": { "total": 193.102992243995, "count": 6310, "is_parallel": true, "self": 99.720220010003, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018527580000409216, "count": 1, "is_parallel": true, "self": 0.0006639319999521831, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011888260000887385, "count": 8, "is_parallel": true, "self": 0.0011888260000887385 } } }, "UnityEnvironment.step": { "total": 0.04300299100009397, "count": 1, "is_parallel": true, "self": 0.0005237480002051598, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004444070000317879, "count": 1, "is_parallel": true, "self": 0.0004444070000317879 }, "communicator.exchange": { "total": 0.04045889500002886, "count": 1, "is_parallel": true, "self": 0.04045889500002886 }, "steps_from_proto": { "total": 0.0015759409998281626, "count": 1, "is_parallel": true, "self": 0.0004257109999343811, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011502299998937815, "count": 8, "is_parallel": true, "self": 0.0011502299998937815 } } } } } } }, "UnityEnvironment.step": { "total": 93.382772233992, "count": 6309, "is_parallel": true, "self": 2.737306260981086, "children": { "UnityEnvironment._generate_step_input": { "total": 2.3092187649936022, "count": 6309, "is_parallel": true, "self": 2.3092187649936022 }, "communicator.exchange": { "total": 79.30013018599698, "count": 6309, "is_parallel": true, "self": 79.30013018599698 }, "steps_from_proto": { "total": 9.036117022020335, "count": 6309, "is_parallel": true, "self": 2.264489650047608, "children": { "_process_rank_one_or_two_observation": { "total": 6.771627371972727, "count": 50472, "is_parallel": true, "self": 6.771627371972727 } } } } } } } } } } }, "trainer_advance": { "total": 72.40474896899673, "count": 6310, "self": 0.1765490229945499, "children": { "process_trajectory": { "total": 16.003313501002594, "count": 6310, "self": 16.003313501002594 }, "_update_policy": { "total": 56.22488644499958, "count": 33, "self": 22.18557770399866, "children": { "TorchPPOOptimizer.update": { "total": 34.03930874100092, "count": 2325, "self": 34.03930874100092 } } } } } } }, "trainer_threads": { "total": 1.0510000265639974e-06, "count": 1, "self": 1.0510000265639974e-06 }, "TrainerController._save_models": { "total": 0.10648813600005269, "count": 1, "self": 0.0016519089999746939, "children": { "RLTrainer._checkpoint": { "total": 0.104836227000078, "count": 1, "self": 0.104836227000078 } } } } } } }