| { | |
| "name": "root", | |
| "gauges": { | |
| "Pyramids.Policy.Entropy.mean": { | |
| "value": 0.2737698554992676, | |
| "min": 0.2737698554992676, | |
| "max": 1.402940273284912, | |
| "count": 100 | |
| }, | |
| "Pyramids.Policy.Entropy.sum": { | |
| "value": 8239.3779296875, | |
| "min": 8239.3779296875, | |
| "max": 42559.59765625, | |
| "count": 100 | |
| }, | |
| "Pyramids.Step.mean": { | |
| "value": 2999941.0, | |
| "min": 29952.0, | |
| "max": 2999941.0, | |
| "count": 100 | |
| }, | |
| "Pyramids.Step.sum": { | |
| "value": 2999941.0, | |
| "min": 29952.0, | |
| "max": 2999941.0, | |
| "count": 100 | |
| }, | |
| "Pyramids.Policy.ExtrinsicValueEstimate.mean": { | |
| "value": 0.4457398056983948, | |
| "min": -0.10019682347774506, | |
| "max": 0.5420278310775757, | |
| "count": 100 | |
| }, | |
| "Pyramids.Policy.ExtrinsicValueEstimate.sum": { | |
| "value": 119.90400695800781, | |
| "min": -24.14743423461914, | |
| "max": 146.88954162597656, | |
| "count": 100 | |
| }, | |
| "Pyramids.Policy.RndValueEstimate.mean": { | |
| "value": -0.0020317237358540297, | |
| "min": -0.033382024616003036, | |
| "max": 0.12539862096309662, | |
| "count": 100 | |
| }, | |
| "Pyramids.Policy.RndValueEstimate.sum": { | |
| "value": -0.5465337038040161, | |
| "min": -8.312124252319336, | |
| "max": 29.71947479248047, | |
| "count": 100 | |
| }, | |
| "Pyramids.Losses.PolicyLoss.mean": { | |
| "value": 0.06909359435110123, | |
| "min": 0.06815462327513695, | |
| "max": 0.07882452072380827, | |
| "count": 100 | |
| }, | |
| "Pyramids.Losses.PolicyLoss.sum": { | |
| "value": 0.9673103209154172, | |
| "min": 0.5195201608807863, | |
| "max": 1.1772807364595257, | |
| "count": 100 | |
| }, | |
| "Pyramids.Losses.ValueLoss.mean": { | |
| "value": 0.011840098765841342, | |
| "min": 7.762069062235192e-06, | |
| "max": 0.013329951953892305, | |
| "count": 100 | |
| }, | |
| "Pyramids.Losses.ValueLoss.sum": { | |
| "value": 0.1657613827217788, | |
| "min": 9.314482874682231e-05, | |
| "max": 0.18957426100314478, | |
| "count": 100 | |
| }, | |
| "Pyramids.Policy.LearningRate.mean": { | |
| "value": 4.918614130000005e-07, | |
| "min": 4.918614130000005e-07, | |
| "max": 9.946118149120001e-05, | |
| "count": 100 | |
| }, | |
| "Pyramids.Policy.LearningRate.sum": { | |
| "value": 6.886059782000007e-06, | |
| "min": 6.886059782000007e-06, | |
| "max": 0.0013231402101931999, | |
| "count": 100 | |
| }, | |
| "Pyramids.Policy.Epsilon.mean": { | |
| "value": 0.1009835238095238, | |
| "min": 0.1009835238095238, | |
| "max": 0.2989223619047619, | |
| "count": 100 | |
| }, | |
| "Pyramids.Policy.Epsilon.sum": { | |
| "value": 1.4137693333333332, | |
| "min": 1.4137693333333332, | |
| "max": 4.046280266666667, | |
| "count": 100 | |
| }, | |
| "Pyramids.Policy.Beta.mean": { | |
| "value": 5.912701428571433e-05, | |
| "min": 5.912701428571433e-05, | |
| "max": 0.009946171977142858, | |
| "count": 100 | |
| }, | |
| "Pyramids.Policy.Beta.sum": { | |
| "value": 0.0008277782000000007, | |
| "min": 0.0008277782000000007, | |
| "max": 0.13232169932, | |
| "count": 100 | |
| }, | |
| "Pyramids.Losses.RNDLoss.mean": { | |
| "value": 0.0010856071021407843, | |
| "min": 0.0010856071021407843, | |
| "max": 0.07840841263532639, | |
| "count": 100 | |
| }, | |
| "Pyramids.Losses.RNDLoss.sum": { | |
| "value": 0.015198498964309692, | |
| "min": 0.015198498964309692, | |
| "max": 0.5488588809967041, | |
| "count": 100 | |
| }, | |
| "Pyramids.Environment.EpisodeLength.mean": { | |
| "value": 420.54794520547944, | |
| "min": 351.5375, | |
| "max": 999.0, | |
| "count": 100 | |
| }, | |
| "Pyramids.Environment.EpisodeLength.sum": { | |
| "value": 30700.0, | |
| "min": 15984.0, | |
| "max": 34260.0, | |
| "count": 100 | |
| }, | |
| "Pyramids.Environment.CumulativeReward.mean": { | |
| "value": 1.3876191502156323, | |
| "min": -1.0000000521540642, | |
| "max": 1.5484424838796258, | |
| "count": 100 | |
| }, | |
| "Pyramids.Environment.CumulativeReward.sum": { | |
| "value": 101.29619796574116, | |
| "min": -30.739201694726944, | |
| "max": 132.84879855066538, | |
| "count": 100 | |
| }, | |
| "Pyramids.Policy.ExtrinsicReward.mean": { | |
| "value": 1.3876191502156323, | |
| "min": -1.0000000521540642, | |
| "max": 1.5484424838796258, | |
| "count": 100 | |
| }, | |
| "Pyramids.Policy.ExtrinsicReward.sum": { | |
| "value": 101.29619796574116, | |
| "min": -30.739201694726944, | |
| "max": 132.84879855066538, | |
| "count": 100 | |
| }, | |
| "Pyramids.Policy.RndReward.mean": { | |
| "value": 0.005058212901319278, | |
| "min": 0.004452020007192914, | |
| "max": 3.542724263621494, | |
| "count": 100 | |
| }, | |
| "Pyramids.Policy.RndReward.sum": { | |
| "value": 0.3692495417963073, | |
| "min": 0.35210325576917967, | |
| "max": 56.68358821794391, | |
| "count": 100 | |
| }, | |
| "Pyramids.IsTraining.mean": { | |
| "value": 1.0, | |
| "min": 1.0, | |
| "max": 1.0, | |
| "count": 100 | |
| }, | |
| "Pyramids.IsTraining.sum": { | |
| "value": 1.0, | |
| "min": 1.0, | |
| "max": 1.0, | |
| "count": 100 | |
| } | |
| }, | |
| "metadata": { | |
| "timer_format_version": "0.1.0", | |
| "start_time_seconds": "1719169236", | |
| "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", | |
| "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 --force", | |
| "mlagents_version": "1.1.0.dev0", | |
| "mlagents_envs_version": "1.1.0.dev0", | |
| "communication_protocol_version": "1.5.0", | |
| "pytorch_version": "2.2.1+cu121", | |
| "numpy_version": "1.23.5", | |
| "end_time_seconds": "1719177232" | |
| }, | |
| "total": 7996.226054188002, | |
| "count": 1, | |
| "self": 0.42982170100003714, | |
| "children": { | |
| "run_training.setup": { | |
| "total": 0.03981155500150635, | |
| "count": 1, | |
| "self": 0.03981155500150635 | |
| }, | |
| "TrainerController.start_learning": { | |
| "total": 7995.756420932001, | |
| "count": 1, | |
| "self": 3.485074950800481, | |
| "children": { | |
| "TrainerController._reset_env": { | |
| "total": 1.5675994770008401, | |
| "count": 1, | |
| "self": 1.5675994770008401 | |
| }, | |
| "TrainerController.advance": { | |
| "total": 7990.513709658195, | |
| "count": 190986, | |
| "self": 3.166204349283362, | |
| "children": { | |
| "env_step": { | |
| "total": 3242.255258412175, | |
| "count": 190986, | |
| "self": 2967.8449710275963, | |
| "children": { | |
| "SubprocessEnvManager._take_step": { | |
| "total": 271.97947607986134, | |
| "count": 190986, | |
| "self": 9.884498323266598, | |
| "children": { | |
| "TorchPolicy.evaluate": { | |
| "total": 262.09497775659474, | |
| "count": 187564, | |
| "self": 262.09497775659474 | |
| } | |
| } | |
| }, | |
| "workers": { | |
| "total": 2.430811304717281, | |
| "count": 190986, | |
| "self": 0.0, | |
| "children": { | |
| "worker_root": { | |
| "total": 7987.663249079316, | |
| "count": 190986, | |
| "is_parallel": true, | |
| "self": 5276.534172413187, | |
| "children": { | |
| "run_training.setup": { | |
| "total": 0.0, | |
| "count": 0, | |
| "is_parallel": true, | |
| "self": 0.0, | |
| "children": { | |
| "steps_from_proto": { | |
| "total": 0.0014355950006574858, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.00043174699931114446, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 0.0010038480013463413, | |
| "count": 8, | |
| "is_parallel": true, | |
| "self": 0.0010038480013463413 | |
| } | |
| } | |
| }, | |
| "UnityEnvironment.step": { | |
| "total": 0.032726117000493105, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.0003178059978381498, | |
| "children": { | |
| "UnityEnvironment._generate_step_input": { | |
| "total": 0.00020648500139941461, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.00020648500139941461 | |
| }, | |
| "communicator.exchange": { | |
| "total": 0.03126808400156733, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.03126808400156733 | |
| }, | |
| "steps_from_proto": { | |
| "total": 0.000933741999688209, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.00020824199964408763, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 0.0007255000000441214, | |
| "count": 8, | |
| "is_parallel": true, | |
| "self": 0.0007255000000441214 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "UnityEnvironment.step": { | |
| "total": 2711.1290766661295, | |
| "count": 190985, | |
| "is_parallel": true, | |
| "self": 45.29417041007582, | |
| "children": { | |
| "UnityEnvironment._generate_step_input": { | |
| "total": 29.67409545886585, | |
| "count": 190985, | |
| "is_parallel": true, | |
| "self": 29.67409545886585 | |
| }, | |
| "communicator.exchange": { | |
| "total": 2518.4234110770103, | |
| "count": 190985, | |
| "is_parallel": true, | |
| "self": 2518.4234110770103 | |
| }, | |
| "steps_from_proto": { | |
| "total": 117.73739972017756, | |
| "count": 190985, | |
| "is_parallel": true, | |
| "self": 30.30138796990468, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 87.43601175027288, | |
| "count": 1527880, | |
| "is_parallel": true, | |
| "self": 87.43601175027288 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "trainer_advance": { | |
| "total": 4745.0922468967365, | |
| "count": 190986, | |
| "self": 7.109252085632761, | |
| "children": { | |
| "process_trajectory": { | |
| "total": 271.04050256012124, | |
| "count": 190986, | |
| "self": 270.18080457012184, | |
| "children": { | |
| "RLTrainer._checkpoint": { | |
| "total": 0.8596979899994039, | |
| "count": 6, | |
| "self": 0.8596979899994039 | |
| } | |
| } | |
| }, | |
| "_update_policy": { | |
| "total": 4466.9424922509825, | |
| "count": 1394, | |
| "self": 1725.7174520399494, | |
| "children": { | |
| "TorchPPOOptimizer.update": { | |
| "total": 2741.225040211033, | |
| "count": 182232, | |
| "self": 2741.225040211033 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "trainer_threads": { | |
| "total": 7.43002601666376e-07, | |
| "count": 1, | |
| "self": 7.43002601666376e-07 | |
| }, | |
| "TrainerController._save_models": { | |
| "total": 0.19003610300205764, | |
| "count": 1, | |
| "self": 0.03214801100330078, | |
| "children": { | |
| "RLTrainer._checkpoint": { | |
| "total": 0.15788809199875686, | |
| "count": 1, | |
| "self": 0.15788809199875686 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } |