| { |
| "name": "root", |
| "gauges": { |
| "Pyramids.Policy.Entropy.mean": { |
| "value": 0.3158121705055237, |
| "min": 0.29496607184410095, |
| "max": 1.410244345664978, |
| "count": 39 |
| }, |
| "Pyramids.Policy.Entropy.sum": { |
| "value": 9393.517578125, |
| "min": 8844.2626953125, |
| "max": 42781.171875, |
| "count": 39 |
| }, |
| "Pyramids.Step.mean": { |
| "value": 1169920.0, |
| "min": 29952.0, |
| "max": 1169920.0, |
| "count": 39 |
| }, |
| "Pyramids.Step.sum": { |
| "value": 1169920.0, |
| "min": 29952.0, |
| "max": 1169920.0, |
| "count": 39 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
| "value": 0.7447579503059387, |
| "min": -0.10438719391822815, |
| "max": 0.7874956130981445, |
| "count": 39 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
| "value": 217.46932983398438, |
| "min": -25.15731430053711, |
| "max": 235.51263427734375, |
| "count": 39 |
| }, |
| "Pyramids.Policy.RndValueEstimate.mean": { |
| "value": 0.0050540645606815815, |
| "min": 0.002281642984598875, |
| "max": 0.3823908567428589, |
| "count": 39 |
| }, |
| "Pyramids.Policy.RndValueEstimate.sum": { |
| "value": 1.475786805152893, |
| "min": 0.6297334432601929, |
| "max": 91.7738037109375, |
| "count": 39 |
| }, |
| "Pyramids.Losses.PolicyLoss.mean": { |
| "value": 0.06952572231341078, |
| "min": 0.0643081430877958, |
| "max": 0.0737794697092011, |
| "count": 39 |
| }, |
| "Pyramids.Losses.PolicyLoss.sum": { |
| "value": 0.9733601123877509, |
| "min": 0.5070515469856689, |
| "max": 1.0985554278886411, |
| "count": 39 |
| }, |
| "Pyramids.Losses.ValueLoss.mean": { |
| "value": 0.015264837785403202, |
| "min": 0.0014053478230961363, |
| "max": 0.01722948211891719, |
| "count": 39 |
| }, |
| "Pyramids.Losses.ValueLoss.sum": { |
| "value": 0.21370772899564483, |
| "min": 0.011333398994605072, |
| "max": 0.24121274966484063, |
| "count": 39 |
| }, |
| "Pyramids.Policy.LearningRate.mean": { |
| "value": 0.00018445010280235957, |
| "min": 0.00018445010280235957, |
| "max": 0.00029838354339596195, |
| "count": 39 |
| }, |
| "Pyramids.Policy.LearningRate.sum": { |
| "value": 0.002582301439233034, |
| "min": 0.0020691136102954665, |
| "max": 0.003982794272401966, |
| "count": 39 |
| }, |
| "Pyramids.Policy.Epsilon.mean": { |
| "value": 0.16148335476190478, |
| "min": 0.16148335476190478, |
| "max": 0.19946118095238097, |
| "count": 39 |
| }, |
| "Pyramids.Policy.Epsilon.sum": { |
| "value": 2.260766966666667, |
| "min": 1.3897045333333333, |
| "max": 2.827598033333333, |
| "count": 39 |
| }, |
| "Pyramids.Policy.Beta.mean": { |
| "value": 0.006152187140714286, |
| "min": 0.006152187140714286, |
| "max": 0.009946171977142856, |
| "count": 39 |
| }, |
| "Pyramids.Policy.Beta.sum": { |
| "value": 0.08613061997, |
| "min": 0.06897148288, |
| "max": 0.13277704353, |
| "count": 39 |
| }, |
| "Pyramids.Losses.RNDLoss.mean": { |
| "value": 0.017058508470654488, |
| "min": 0.016507115215063095, |
| "max": 0.41962990164756775, |
| "count": 39 |
| }, |
| "Pyramids.Losses.RNDLoss.sum": { |
| "value": 0.23881910741329193, |
| "min": 0.23109962046146393, |
| "max": 2.9374094009399414, |
| "count": 39 |
| }, |
| "Pyramids.Environment.EpisodeLength.mean": { |
| "value": 239.27777777777777, |
| "min": 239.27777777777777, |
| "max": 999.0, |
| "count": 39 |
| }, |
| "Pyramids.Environment.EpisodeLength.sum": { |
| "value": 30149.0, |
| "min": 15984.0, |
| "max": 32429.0, |
| "count": 39 |
| }, |
| "Pyramids.Environment.CumulativeReward.mean": { |
| "value": 1.743537591457367, |
| "min": -1.0000000521540642, |
| "max": 1.743537591457367, |
| "count": 39 |
| }, |
| "Pyramids.Environment.CumulativeReward.sum": { |
| "value": 217.94219893217087, |
| "min": -32.000001668930054, |
| "max": 219.57759799063206, |
| "count": 39 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.mean": { |
| "value": 1.743537591457367, |
| "min": -1.0000000521540642, |
| "max": 1.743537591457367, |
| "count": 39 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.sum": { |
| "value": 217.94219893217087, |
| "min": -32.000001668930054, |
| "max": 219.57759799063206, |
| "count": 39 |
| }, |
| "Pyramids.Policy.RndReward.mean": { |
| "value": 0.04244775066198781, |
| "min": 0.04201625723269386, |
| "max": 8.009627480991185, |
| "count": 39 |
| }, |
| "Pyramids.Policy.RndReward.sum": { |
| "value": 5.305968832748476, |
| "min": 4.84608137619216, |
| "max": 128.15403969585896, |
| "count": 39 |
| }, |
| "Pyramids.IsTraining.mean": { |
| "value": 1.0, |
| "min": 1.0, |
| "max": 1.0, |
| "count": 39 |
| }, |
| "Pyramids.IsTraining.sum": { |
| "value": 1.0, |
| "min": 1.0, |
| "max": 1.0, |
| "count": 39 |
| } |
| }, |
| "metadata": { |
| "timer_format_version": "0.1.0", |
| "start_time_seconds": "1749305463", |
| "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": "2.7.1+cu126", |
| "numpy_version": "1.23.5", |
| "end_time_seconds": "1749308239" |
| }, |
| "total": 2775.9240816079996, |
| "count": 1, |
| "self": 0.45353642199916067, |
| "children": { |
| "run_training.setup": { |
| "total": 0.027403502000197477, |
| "count": 1, |
| "self": 0.027403502000197477 |
| }, |
| "TrainerController.start_learning": { |
| "total": 2775.4431416840002, |
| "count": 1, |
| "self": 1.6428113899801247, |
| "children": { |
| "TrainerController._reset_env": { |
| "total": 2.8092710209998586, |
| "count": 1, |
| "self": 2.8092710209998586 |
| }, |
| "TrainerController.advance": { |
| "total": 2770.85612705102, |
| "count": 75712, |
| "self": 1.6674976367771706, |
| "children": { |
| "env_step": { |
| "total": 1965.0553908501329, |
| "count": 75712, |
| "self": 1782.6454615121643, |
| "children": { |
| "SubprocessEnvManager._take_step": { |
| "total": 181.41729345891372, |
| "count": 75712, |
| "self": 5.513984144850383, |
| "children": { |
| "TorchPolicy.evaluate": { |
| "total": 175.90330931406334, |
| "count": 73458, |
| "self": 175.90330931406334 |
| } |
| } |
| }, |
| "workers": { |
| "total": 0.9926358790548875, |
| "count": 75711, |
| "self": 0.0, |
| "children": { |
| "worker_root": { |
| "total": 2769.3960856070203, |
| "count": 75711, |
| "is_parallel": true, |
| "self": 1121.852393286943, |
| "children": { |
| "run_training.setup": { |
| "total": 0.0, |
| "count": 0, |
| "is_parallel": true, |
| "self": 0.0, |
| "children": { |
| "steps_from_proto": { |
| "total": 0.0019828189997497248, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0007115350008461974, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0012712839989035274, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.0012712839989035274 |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 0.04465047100029551, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0004885019998255302, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 0.0004643070001293381, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0004643070001293381 |
| }, |
| "communicator.exchange": { |
| "total": 0.04226792100007515, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.04226792100007515 |
| }, |
| "steps_from_proto": { |
| "total": 0.0014297410002654942, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.00029010499974901904, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0011396360005164752, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.0011396360005164752 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 1647.5436923200773, |
| "count": 75710, |
| "is_parallel": true, |
| "self": 37.149034059001224, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 27.126833855074892, |
| "count": 75710, |
| "is_parallel": true, |
| "self": 27.126833855074892 |
| }, |
| "communicator.exchange": { |
| "total": 1469.8331299670613, |
| "count": 75710, |
| "is_parallel": true, |
| "self": 1469.8331299670613 |
| }, |
| "steps_from_proto": { |
| "total": 113.43469443893991, |
| "count": 75710, |
| "is_parallel": true, |
| "self": 23.059723785009737, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 90.37497065393018, |
| "count": 605680, |
| "is_parallel": true, |
| "self": 90.37497065393018 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_advance": { |
| "total": 804.1332385641099, |
| "count": 75711, |
| "self": 3.2211950250607515, |
| "children": { |
| "process_trajectory": { |
| "total": 156.1800413140536, |
| "count": 75711, |
| "self": 155.98443339305368, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.19560792099991886, |
| "count": 2, |
| "self": 0.19560792099991886 |
| } |
| } |
| }, |
| "_update_policy": { |
| "total": 644.7320022249955, |
| "count": 530, |
| "self": 358.1047951579808, |
| "children": { |
| "TorchPPOOptimizer.update": { |
| "total": 286.62720706701475, |
| "count": 26781, |
| "self": 286.62720706701475 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_threads": { |
| "total": 1.5000005078036338e-06, |
| "count": 1, |
| "self": 1.5000005078036338e-06 |
| }, |
| "TrainerController._save_models": { |
| "total": 0.13493072199980816, |
| "count": 1, |
| "self": 0.00162711200027843, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.13330360999952973, |
| "count": 1, |
| "self": 0.13330360999952973 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
