| { |
| "name": "root", |
| "gauges": { |
| "Pyramids.Policy.Entropy.mean": { |
| "value": 0.394096314907074, |
| "min": 0.394096314907074, |
| "max": 1.5931488275527954, |
| "count": 66 |
| }, |
| "Pyramids.Policy.Entropy.sum": { |
| "value": 11911.1669921875, |
| "min": 11737.861328125, |
| "max": 48329.76171875, |
| "count": 66 |
| }, |
| "Pyramids.Step.mean": { |
| "value": 1979972.0, |
| "min": 29952.0, |
| "max": 1979972.0, |
| "count": 66 |
| }, |
| "Pyramids.Step.sum": { |
| "value": 1979972.0, |
| "min": 29952.0, |
| "max": 1979972.0, |
| "count": 66 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
| "value": 0.7865497469902039, |
| "min": -0.07652597874403, |
| "max": 0.8273004293441772, |
| "count": 66 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
| "value": 239.89767456054688, |
| "min": -18.442760467529297, |
| "max": 251.49932861328125, |
| "count": 66 |
| }, |
| "Pyramids.Policy.RndValueEstimate.mean": { |
| "value": 0.0009274151525460184, |
| "min": -0.03034655936062336, |
| "max": 0.3043420910835266, |
| "count": 66 |
| }, |
| "Pyramids.Policy.RndValueEstimate.sum": { |
| "value": 0.2828616201877594, |
| "min": -8.375650405883789, |
| "max": 73.04209899902344, |
| "count": 66 |
| }, |
| "Pyramids.Losses.PolicyLoss.mean": { |
| "value": 0.04824310678781735, |
| "min": 0.044827858877963284, |
| "max": 0.05495047441386766, |
| "count": 66 |
| }, |
| "Pyramids.Losses.PolicyLoss.sum": { |
| "value": 0.14472932036345204, |
| "min": 0.09485094993142411, |
| "max": 0.16242758565737556, |
| "count": 66 |
| }, |
| "Pyramids.Losses.ValueLoss.mean": { |
| "value": 0.014282432970746111, |
| "min": 0.0002758280516635327, |
| "max": 0.01667613777357878, |
| "count": 66 |
| }, |
| "Pyramids.Losses.ValueLoss.sum": { |
| "value": 0.04284729891223833, |
| "min": 0.0008274841549905981, |
| "max": 0.05002841332073635, |
| "count": 66 |
| }, |
| "Pyramids.Policy.LearningRate.mean": { |
| "value": 5.059398313566666e-06, |
| "min": 5.059398313566666e-06, |
| "max": 0.00029726400091199996, |
| "count": 66 |
| }, |
| "Pyramids.Policy.LearningRate.sum": { |
| "value": 1.5178194940699999e-05, |
| "min": 1.5178194940699999e-05, |
| "max": 0.0008675136108288, |
| "count": 66 |
| }, |
| "Pyramids.Policy.Epsilon.mean": { |
| "value": 0.10168643333333334, |
| "min": 0.10168643333333334, |
| "max": 0.19908800000000001, |
| "count": 66 |
| }, |
| "Pyramids.Policy.Epsilon.sum": { |
| "value": 0.30505930000000003, |
| "min": 0.22449950000000002, |
| "max": 0.5891712000000001, |
| "count": 66 |
| }, |
| "Pyramids.Policy.Beta.mean": { |
| "value": 0.00017847469, |
| "min": 0.00017847469, |
| "max": 0.0099088912, |
| "count": 66 |
| }, |
| "Pyramids.Policy.Beta.sum": { |
| "value": 0.00053542407, |
| "min": 0.00053542407, |
| "max": 0.02891820288, |
| "count": 66 |
| }, |
| "Pyramids.Losses.RNDLoss.mean": { |
| "value": 0.007424440234899521, |
| "min": 0.0072309039533138275, |
| "max": 0.41286998987197876, |
| "count": 66 |
| }, |
| "Pyramids.Losses.RNDLoss.sum": { |
| "value": 0.022273320704698563, |
| "min": 0.015569616109132767, |
| "max": 0.8257399797439575, |
| "count": 66 |
| }, |
| "Pyramids.Environment.EpisodeLength.mean": { |
| "value": 251.9609375, |
| "min": 216.30714285714285, |
| "max": 999.0, |
| "count": 66 |
| }, |
| "Pyramids.Environment.EpisodeLength.sum": { |
| "value": 32251.0, |
| "min": 15984.0, |
| "max": 33099.0, |
| "count": 66 |
| }, |
| "Pyramids.Environment.CumulativeReward.mean": { |
| "value": 1.7011468599084765, |
| "min": -1.0000000521540642, |
| "max": 1.7694057043109621, |
| "count": 66 |
| }, |
| "Pyramids.Environment.CumulativeReward.sum": { |
| "value": 217.746798068285, |
| "min": -32.000001668930054, |
| "max": 247.7167986035347, |
| "count": 66 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.mean": { |
| "value": 1.7011468599084765, |
| "min": -1.0000000521540642, |
| "max": 1.7694057043109621, |
| "count": 66 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.sum": { |
| "value": 217.746798068285, |
| "min": -32.000001668930054, |
| "max": 247.7167986035347, |
| "count": 66 |
| }, |
| "Pyramids.Policy.RndReward.mean": { |
| "value": 0.019332847940745523, |
| "min": 0.01694411945592085, |
| "max": 9.185593564994633, |
| "count": 66 |
| }, |
| "Pyramids.Policy.RndReward.sum": { |
| "value": 2.474604536415427, |
| "min": 2.134660757277743, |
| "max": 146.96949703991413, |
| "count": 66 |
| }, |
| "Pyramids.IsTraining.mean": { |
| "value": 1.0, |
| "min": 1.0, |
| "max": 1.0, |
| "count": 66 |
| }, |
| "Pyramids.IsTraining.sum": { |
| "value": 1.0, |
| "min": 1.0, |
| "max": 1.0, |
| "count": 66 |
| } |
| }, |
| "metadata": { |
| "timer_format_version": "0.1.0", |
| "start_time_seconds": "1712008683", |
| "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 2 --no-graphics", |
| "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": "1712013406" |
| }, |
| "total": 4723.0970365329995, |
| "count": 1, |
| "self": 1.0374969789991155, |
| "children": { |
| "run_training.setup": { |
| "total": 0.055171050999888394, |
| "count": 1, |
| "self": 0.055171050999888394 |
| }, |
| "TrainerController.start_learning": { |
| "total": 4722.0043685030005, |
| "count": 1, |
| "self": 3.2938663727081803, |
| "children": { |
| "TrainerController._reset_env": { |
| "total": 2.19418726099957, |
| "count": 1, |
| "self": 2.19418726099957 |
| }, |
| "TrainerController.advance": { |
| "total": 4716.338854054292, |
| "count": 129368, |
| "self": 3.310938320922105, |
| "children": { |
| "env_step": { |
| "total": 3637.200740021185, |
| "count": 129368, |
| "self": 3337.633276229848, |
| "children": { |
| "SubprocessEnvManager._take_step": { |
| "total": 297.6042357238057, |
| "count": 129368, |
| "self": 10.380849655987731, |
| "children": { |
| "TorchPolicy.evaluate": { |
| "total": 287.22338606781796, |
| "count": 125055, |
| "self": 287.22338606781796 |
| } |
| } |
| }, |
| "workers": { |
| "total": 1.9632280675314178, |
| "count": 129368, |
| "self": 0.0, |
| "children": { |
| "worker_root": { |
| "total": 4710.571794474072, |
| "count": 129368, |
| "is_parallel": true, |
| "self": 1641.5904376210246, |
| "children": { |
| "run_training.setup": { |
| "total": 0.0, |
| "count": 0, |
| "is_parallel": true, |
| "self": 0.0, |
| "children": { |
| "steps_from_proto": { |
| "total": 0.0022729100001015468, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0007136340009310516, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0015592759991704952, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.0015592759991704952 |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 0.06694451099974685, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0006785599989598268, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 0.0005097709999972722, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0005097709999972722 |
| }, |
| "communicator.exchange": { |
| "total": 0.06382174100053817, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.06382174100053817 |
| }, |
| "steps_from_proto": { |
| "total": 0.0019344390002515865, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0004822910013899673, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0014521479988616193, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.0014521479988616193 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 3068.981356853047, |
| "count": 129367, |
| "is_parallel": true, |
| "self": 72.9834660516417, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 51.02761133595959, |
| "count": 129367, |
| "is_parallel": true, |
| "self": 51.02761133595959 |
| }, |
| "communicator.exchange": { |
| "total": 2726.704107226841, |
| "count": 129367, |
| "is_parallel": true, |
| "self": 2726.704107226841 |
| }, |
| "steps_from_proto": { |
| "total": 218.26617223860467, |
| "count": 129367, |
| "is_parallel": true, |
| "self": 45.748414136016436, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 172.51775810258823, |
| "count": 1034936, |
| "is_parallel": true, |
| "self": 172.51775810258823 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_advance": { |
| "total": 1075.8271757121847, |
| "count": 129368, |
| "self": 6.173248033425807, |
| "children": { |
| "process_trajectory": { |
| "total": 283.93078335974496, |
| "count": 129368, |
| "self": 283.279092568745, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.6516907909999645, |
| "count": 4, |
| "self": 0.6516907909999645 |
| } |
| } |
| }, |
| "_update_policy": { |
| "total": 785.723144319014, |
| "count": 192, |
| "self": 533.8235544419049, |
| "children": { |
| "TorchPPOOptimizer.update": { |
| "total": 251.89958987710907, |
| "count": 23256, |
| "self": 251.89958987710907 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_threads": { |
| "total": 1.4430006558541209e-06, |
| "count": 1, |
| "self": 1.4430006558541209e-06 |
| }, |
| "TrainerController._save_models": { |
| "total": 0.1774593720001576, |
| "count": 1, |
| "self": 0.0029443370003718883, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.1745150349997857, |
| "count": 1, |
| "self": 0.1745150349997857 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
