{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.48972946405410767, "min": 0.48972946405410767, "max": 1.474390983581543, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 14691.8837890625, "min": 14691.8837890625, "max": 44727.125, "count": 33 }, "Pyramids.Step.mean": { "value": 989888.0, "min": 29952.0, "max": 989888.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989888.0, "min": 29952.0, "max": 989888.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.565028965473175, "min": -0.10292492806911469, "max": 0.565028965473175, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 159.33816528320312, "min": -24.804906845092773, "max": 159.33816528320312, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.041117772459983826, "min": -0.041117772459983826, "max": 0.3238210678100586, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -11.59521198272705, "min": -11.59521198272705, "max": 76.74559020996094, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06793856926378793, "min": 0.06620287669478207, "max": 0.07304457563962997, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.951139969693031, "min": 0.48757065038481756, "max": 1.0534353238569263, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015523078885356274, "min": 0.001062336317346016, "max": 0.01605458273271714, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21732310439498784, "min": 0.008118052044759178, "max": 0.22668186703231183, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.366640401628573e-06, "min": 7.366640401628573e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010313296562280002, "min": 0.00010313296562280002, "max": 0.003507210230929999, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10245551428571428, "min": 0.10245551428571428, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4343772, "min": 1.3691136000000002, "max": 2.5690700000000004, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025530587714285726, "min": 0.00025530587714285726, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035742822800000013, "min": 0.0035742822800000013, "max": 0.11693009300000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.008065718226134777, "min": 0.008065718226134777, "max": 0.356244832277298, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.11292005330324173, "min": 0.11292005330324173, "max": 2.493713855743408, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 359.3953488372093, "min": 342.9294117647059, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30908.0, "min": 15984.0, "max": 32255.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.570827882823556, "min": -1.0000000521540642, "max": 1.5992333186524255, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 135.0911979228258, "min": -32.000001668930054, "max": 135.0911979228258, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.570827882823556, "min": -1.0000000521540642, "max": 1.5992333186524255, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 135.0911979228258, "min": -32.000001668930054, "max": 135.0911979228258, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.029611377594762397, "min": 0.029104226777631352, "max": 7.184065002948046, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.546578473149566, "min": 2.473859276098665, "max": 114.94504004716873, "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": "1779277664", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1779280237" }, "total": 2572.9137151450004, "count": 1, "self": 0.5298362009998527, "children": { "run_training.setup": { "total": 0.025637374000325508, "count": 1, "self": 0.025637374000325508 }, "TrainerController.start_learning": { "total": 2572.3582415700002, "count": 1, "self": 1.6268345269245401, "children": { "TrainerController._reset_env": { "total": 2.82642911000039, "count": 1, "self": 2.82642911000039 }, "TrainerController.advance": { "total": 2567.8278099520767, "count": 63769, "self": 1.6791940240082113, "children": { "env_step": { "total": 1870.0002010780545, "count": 63769, "self": 1698.7250152680763, "children": { "SubprocessEnvManager._take_step": { "total": 170.28273479495783, "count": 63769, "self": 5.108184689975133, "children": { "TorchPolicy.evaluate": { "total": 165.1745501049827, "count": 62575, "self": 165.1745501049827 } } }, "workers": { "total": 0.9924510150203787, "count": 63769, "self": 0.0, "children": { "worker_root": { "total": 2566.376482418089, "count": 63769, "is_parallel": true, "self": 998.0227530982465, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0019236359994465602, "count": 1, "is_parallel": true, "self": 0.0005876449977222364, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013359910017243237, "count": 8, "is_parallel": true, "self": 0.0013359910017243237 } } }, "UnityEnvironment.step": { "total": 0.09471860700068646, "count": 1, "is_parallel": true, "self": 0.0016011310008252622, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004042820000904612, "count": 1, "is_parallel": true, "self": 0.0004042820000904612 }, "communicator.exchange": { "total": 0.09000329099944793, "count": 1, "is_parallel": true, "self": 0.09000329099944793 }, "steps_from_proto": { "total": 0.002709903000322811, "count": 1, "is_parallel": true, "self": 0.0003501819992379751, "children": { "_process_rank_one_or_two_observation": { "total": 0.0023597210010848357, "count": 8, "is_parallel": true, "self": 0.0023597210010848357 } } } } } } }, "UnityEnvironment.step": { "total": 1568.3537293198424, "count": 63768, "is_parallel": true, "self": 36.13277897959961, "children": { "UnityEnvironment._generate_step_input": { "total": 25.097316204987692, "count": 63768, "is_parallel": true, "self": 25.097316204987692 }, "communicator.exchange": { "total": 1388.791726015048, "count": 63768, "is_parallel": true, "self": 1388.791726015048 }, "steps_from_proto": { "total": 118.33190812020712, "count": 63768, "is_parallel": true, "self": 24.654857846686355, "children": { "_process_rank_one_or_two_observation": { "total": 93.67705027352076, "count": 510144, "is_parallel": true, "self": 93.67705027352076 } } } } } } } } } } }, "trainer_advance": { "total": 696.148414850014, "count": 63769, "self": 3.072574777086629, "children": { "process_trajectory": { "total": 135.04014503693816, "count": 63769, "self": 134.83776335193943, "children": { "RLTrainer._checkpoint": { "total": 0.202381684998727, "count": 2, "self": 0.202381684998727 } } }, "_update_policy": { "total": 558.0356950359892, "count": 447, "self": 308.9589092230326, "children": { "TorchPPOOptimizer.update": { "total": 249.0767858129566, "count": 22830, "self": 249.0767858129566 } } } } } } }, "trainer_threads": { "total": 8.979986887425184e-07, "count": 1, "self": 8.979986887425184e-07 }, "TrainerController._save_models": { "total": 0.07716708299994934, "count": 1, "self": 0.0012263829994481057, "children": { "RLTrainer._checkpoint": { "total": 0.07594070000050124, "count": 1, "self": 0.07594070000050124 } } } } } } }