| { |
| "name": "root", |
| "gauges": { |
| "Pyramids.Policy.Entropy.mean": { |
| "value": 0.15264427661895752, |
| "min": 0.14875833690166473, |
| "max": 1.421367883682251, |
| "count": 100 |
| }, |
| "Pyramids.Policy.Entropy.sum": { |
| "value": 4523.1552734375, |
| "min": 4453.2294921875, |
| "max": 43118.6171875, |
| "count": 100 |
| }, |
| "Pyramids.Step.mean": { |
| "value": 2999921.0, |
| "min": 29952.0, |
| "max": 2999921.0, |
| "count": 100 |
| }, |
| "Pyramids.Step.sum": { |
| "value": 2999921.0, |
| "min": 29952.0, |
| "max": 2999921.0, |
| "count": 100 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
| "value": 0.7322972416877747, |
| "min": -0.08542553335428238, |
| "max": 0.8861995339393616, |
| "count": 100 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
| "value": 214.56309509277344, |
| "min": -20.587553024291992, |
| "max": 267.63226318359375, |
| "count": 100 |
| }, |
| "Pyramids.Policy.RndValueEstimate.mean": { |
| "value": -0.006753959227353334, |
| "min": -0.026859920471906662, |
| "max": 0.3976025879383087, |
| "count": 100 |
| }, |
| "Pyramids.Policy.RndValueEstimate.sum": { |
| "value": -1.9789100885391235, |
| "min": -7.950536727905273, |
| "max": 94.2318115234375, |
| "count": 100 |
| }, |
| "Pyramids.Losses.PolicyLoss.mean": { |
| "value": 0.07141281092125508, |
| "min": 0.06502505257078094, |
| "max": 0.07400694290480604, |
| "count": 100 |
| }, |
| "Pyramids.Losses.PolicyLoss.sum": { |
| "value": 1.0711921638188262, |
| "min": 0.48338116885292687, |
| "max": 1.0843399366179558, |
| "count": 100 |
| }, |
| "Pyramids.Losses.ValueLoss.mean": { |
| "value": 0.014056059248590222, |
| "min": 0.0005011016105033887, |
| "max": 0.016606580748754953, |
| "count": 100 |
| }, |
| "Pyramids.Losses.ValueLoss.sum": { |
| "value": 0.21084088872885334, |
| "min": 0.0067195795845796, |
| "max": 0.24122597727303702, |
| "count": 100 |
| }, |
| "Pyramids.Policy.LearningRate.mean": { |
| "value": 1.4875661708444438e-06, |
| "min": 1.4875661708444438e-06, |
| "max": 0.00029838354339596195, |
| "count": 100 |
| }, |
| "Pyramids.Policy.LearningRate.sum": { |
| "value": 2.2313492562666657e-05, |
| "min": 2.2313492562666657e-05, |
| "max": 0.004011372562875833, |
| "count": 100 |
| }, |
| "Pyramids.Policy.Epsilon.mean": { |
| "value": 0.10049582222222225, |
| "min": 0.10049582222222225, |
| "max": 0.19946118095238097, |
| "count": 100 |
| }, |
| "Pyramids.Policy.Epsilon.sum": { |
| "value": 1.5074373333333337, |
| "min": 1.3897045333333333, |
| "max": 2.767387966666667, |
| "count": 100 |
| }, |
| "Pyramids.Policy.Beta.mean": { |
| "value": 5.953263999999997e-05, |
| "min": 5.953263999999997e-05, |
| "max": 0.009946171977142856, |
| "count": 100 |
| }, |
| "Pyramids.Policy.Beta.sum": { |
| "value": 0.0008929895999999995, |
| "min": 0.0008929895999999995, |
| "max": 0.13371870425, |
| "count": 100 |
| }, |
| "Pyramids.Losses.RNDLoss.mean": { |
| "value": 0.008005733601748943, |
| "min": 0.007956665940582752, |
| "max": 0.47914454340934753, |
| "count": 100 |
| }, |
| "Pyramids.Losses.RNDLoss.sum": { |
| "value": 0.12008599936962128, |
| "min": 0.11371825635433197, |
| "max": 3.3540117740631104, |
| "count": 100 |
| }, |
| "Pyramids.Environment.EpisodeLength.mean": { |
| "value": 244.60330578512398, |
| "min": 213.09558823529412, |
| "max": 999.0, |
| "count": 100 |
| }, |
| "Pyramids.Environment.EpisodeLength.sum": { |
| "value": 29597.0, |
| "min": 15984.0, |
| "max": 32956.0, |
| "count": 100 |
| }, |
| "Pyramids.Environment.CumulativeReward.mean": { |
| "value": 1.7057933727941237, |
| "min": -1.0000000521540642, |
| "max": 1.7847323797538246, |
| "count": 100 |
| }, |
| "Pyramids.Environment.CumulativeReward.sum": { |
| "value": 206.40099810808897, |
| "min": -32.000001668930054, |
| "max": 253.4319979250431, |
| "count": 100 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.mean": { |
| "value": 1.7057933727941237, |
| "min": -1.0000000521540642, |
| "max": 1.7847323797538246, |
| "count": 100 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.sum": { |
| "value": 206.40099810808897, |
| "min": -32.000001668930054, |
| "max": 253.4319979250431, |
| "count": 100 |
| }, |
| "Pyramids.Policy.RndReward.mean": { |
| "value": 0.020315840067494657, |
| "min": 0.01813923755520698, |
| "max": 9.420676331967115, |
| "count": 100 |
| }, |
| "Pyramids.Policy.RndReward.sum": { |
| "value": 2.4582166481668537, |
| "min": 2.3398864229675382, |
| "max": 150.73082131147385, |
| "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": "1699842738", |
| "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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", |
| "mlagents_version": "1.1.0.dev0", |
| "mlagents_envs_version": "1.1.0.dev0", |
| "communication_protocol_version": "1.5.0", |
| "pytorch_version": "2.1.0+cu118", |
| "numpy_version": "1.23.5", |
| "end_time_seconds": "1699854367" |
| }, |
| "total": 11628.692556547001, |
| "count": 1, |
| "self": 0.5929725250007323, |
| "children": { |
| "run_training.setup": { |
| "total": 0.08970363100000611, |
| "count": 1, |
| "self": 0.08970363100000611 |
| }, |
| "TrainerController.start_learning": { |
| "total": 11628.009880391, |
| "count": 1, |
| "self": 7.10266662228787, |
| "children": { |
| "TrainerController._reset_env": { |
| "total": 2.489865047000009, |
| "count": 1, |
| "self": 2.489865047000009 |
| }, |
| "TrainerController.advance": { |
| "total": 11618.329247201713, |
| "count": 195312, |
| "self": 7.629922838177663, |
| "children": { |
| "env_step": { |
| "total": 8093.727919174896, |
| "count": 195312, |
| "self": 7598.207967884882, |
| "children": { |
| "SubprocessEnvManager._take_step": { |
| "total": 491.385127705939, |
| "count": 195312, |
| "self": 23.34510865057166, |
| "children": { |
| "TorchPolicy.evaluate": { |
| "total": 468.04001905536734, |
| "count": 187542, |
| "self": 468.04001905536734 |
| } |
| } |
| }, |
| "workers": { |
| "total": 4.1348235840745104, |
| "count": 195312, |
| "self": 0.0, |
| "children": { |
| "worker_root": { |
| "total": 11606.105835073062, |
| "count": 195312, |
| "is_parallel": true, |
| "self": 4554.616875704965, |
| "children": { |
| "run_training.setup": { |
| "total": 0.0, |
| "count": 0, |
| "is_parallel": true, |
| "self": 0.0, |
| "children": { |
| "steps_from_proto": { |
| "total": 0.0054555180000050996, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0033377630000046565, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.002117755000000443, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.002117755000000443 |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 0.09856738500000972, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0006943260000156215, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 0.0004934629999979734, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0004934629999979734 |
| }, |
| "communicator.exchange": { |
| "total": 0.09548719100000369, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.09548719100000369 |
| }, |
| "steps_from_proto": { |
| "total": 0.0018924049999924364, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.00039456299998619215, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0014978420000062442, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.0014978420000062442 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 7051.488959368096, |
| "count": 195311, |
| "is_parallel": true, |
| "self": 141.8678052567302, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 88.00314993003958, |
| "count": 195311, |
| "is_parallel": true, |
| "self": 88.00314993003958 |
| }, |
| "communicator.exchange": { |
| "total": 6428.001605016134, |
| "count": 195311, |
| "is_parallel": true, |
| "self": 6428.001605016134 |
| }, |
| "steps_from_proto": { |
| "total": 393.61639916519266, |
| "count": 195311, |
| "is_parallel": true, |
| "self": 84.83922773136715, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 308.7771714338255, |
| "count": 1562488, |
| "is_parallel": true, |
| "self": 308.7771714338255 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_advance": { |
| "total": 3516.9714051886394, |
| "count": 195312, |
| "self": 14.375925529996493, |
| "children": { |
| "process_trajectory": { |
| "total": 516.3305875696669, |
| "count": 195312, |
| "self": 515.7516080776652, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.5789794920017357, |
| "count": 6, |
| "self": 0.5789794920017357 |
| } |
| } |
| }, |
| "_update_policy": { |
| "total": 2986.264892088976, |
| "count": 1392, |
| "self": 1173.5918048160993, |
| "children": { |
| "TorchPPOOptimizer.update": { |
| "total": 1812.6730872728767, |
| "count": 68421, |
| "self": 1812.6730872728767 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_threads": { |
| "total": 1.128999429056421e-06, |
| "count": 1, |
| "self": 1.128999429056421e-06 |
| }, |
| "TrainerController._save_models": { |
| "total": 0.08810039099989808, |
| "count": 1, |
| "self": 0.001915490000101272, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.08618490099979681, |
| "count": 1, |
| "self": 0.08618490099979681 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
