{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4242022633552551, "min": 0.4242022633552551, "max": 1.4047181606292725, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 12685.3447265625, "min": 12685.3447265625, "max": 42613.53125, "count": 33 }, "Pyramids.Step.mean": { "value": 989899.0, "min": 29952.0, "max": 989899.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989899.0, "min": 29952.0, "max": 989899.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.525754451751709, "min": -0.10555518418550491, "max": 0.5750319957733154, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 145.6339874267578, "min": -25.33324432373047, "max": 159.85888671875, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.010865925811231136, "min": -0.03466660529375076, "max": 0.319426953792572, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -3.009861469268799, "min": -9.637316703796387, "max": 75.70418548583984, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06844507793097623, "min": 0.06469114651970033, "max": 0.07419982659608015, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9582310910336672, "min": 0.4953595549316446, "max": 1.057088388421107, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014447541673213157, "min": 0.0006516272875706804, "max": 0.01602260360232322, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.20226558342498419, "min": 0.004561391012994763, "max": 0.23635667720159023, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.679776011535713e-06, "min": 7.679776011535713e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010751686416149999, "min": 0.00010751686416149999, "max": 0.0035073230308923994, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10255989285714287, "min": 0.10255989285714287, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4358385000000002, "min": 1.3691136000000002, "max": 2.5691075999999997, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002657332964285714, "min": 0.0002657332964285714, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0037202661499999993, "min": 0.0037202661499999993, "max": 0.11693384923999998, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.011006060056388378, "min": 0.011006060056388378, "max": 0.48792916536331177, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.15408484637737274, "min": 0.15408484637737274, "max": 3.415504217147827, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 360.45238095238096, "min": 331.8876404494382, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30278.0, "min": 15984.0, "max": 34029.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5204737897784937, "min": -1.0000000521540642, "max": 1.6127221991618474, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 127.71979834139347, "min": -32.000001668930054, "max": 145.14499792456627, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5204737897784937, "min": -1.0000000521540642, "max": 1.6127221991618474, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 127.71979834139347, "min": -32.000001668930054, "max": 145.14499792456627, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.041196011354865426, "min": 0.040527268927649, "max": 10.124031292274594, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.460464953808696, "min": 3.4378314115456305, "max": 161.9845006763935, "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": "1745202176", "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": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1745204346" }, "total": 2170.028992998, "count": 1, "self": 0.8029229690000648, "children": { "run_training.setup": { "total": 0.02122372499991343, "count": 1, "self": 0.02122372499991343 }, "TrainerController.start_learning": { "total": 2169.204846304, "count": 1, "self": 1.2804055779888586, "children": { "TrainerController._reset_env": { "total": 3.0859306439999727, "count": 1, "self": 3.0859306439999727 }, "TrainerController.advance": { "total": 2164.7136669990114, "count": 63862, "self": 1.3754721899977085, "children": { "env_step": { "total": 1482.5907729259916, "count": 63862, "self": 1331.1922269039715, "children": { "SubprocessEnvManager._take_step": { "total": 150.65186416097345, "count": 63862, "self": 4.525923154971565, "children": { "TorchPolicy.evaluate": { "total": 146.12594100600188, "count": 62560, "self": 146.12594100600188 } } }, "workers": { "total": 0.7466818610466817, "count": 63862, "self": 0.0, "children": { "worker_root": { "total": 2164.702220034001, "count": 63862, "is_parallel": true, "self": 942.1222213940273, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0061355640000329, "count": 1, "is_parallel": true, "self": 0.004557420999958595, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015781430000743057, "count": 8, "is_parallel": true, "self": 0.0015781430000743057 } } }, "UnityEnvironment.step": { "total": 0.04959640499998841, "count": 1, "is_parallel": true, "self": 0.0005299799998965682, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005042330000151196, "count": 1, "is_parallel": true, "self": 0.0005042330000151196 }, "communicator.exchange": { "total": 0.04693006500008323, "count": 1, "is_parallel": true, "self": 0.04693006500008323 }, "steps_from_proto": { "total": 0.0016321269999934884, "count": 1, "is_parallel": true, "self": 0.0003534699999363511, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012786570000571373, "count": 8, "is_parallel": true, "self": 0.0012786570000571373 } } } } } } }, "UnityEnvironment.step": { "total": 1222.5799986399738, "count": 63861, "is_parallel": true, "self": 31.166389917934794, "children": { "UnityEnvironment._generate_step_input": { "total": 22.830750421007792, "count": 63861, "is_parallel": true, "self": 22.830750421007792 }, "communicator.exchange": { "total": 1073.8533464900484, "count": 63861, "is_parallel": true, "self": 1073.8533464900484 }, "steps_from_proto": { "total": 94.72951181098279, "count": 63861, "is_parallel": true, "self": 19.106763246041737, "children": { "_process_rank_one_or_two_observation": { "total": 75.62274856494105, "count": 510888, "is_parallel": true, "self": 75.62274856494105 } } } } } } } } } } }, "trainer_advance": { "total": 680.7474218830223, "count": 63862, "self": 2.480106804121874, "children": { "process_trajectory": { "total": 128.0592238229026, "count": 63862, "self": 127.74714167490265, "children": { "RLTrainer._checkpoint": { "total": 0.31208214799994494, "count": 2, "self": 0.31208214799994494 } } }, "_update_policy": { "total": 550.2080912559978, "count": 446, "self": 304.0616761860093, "children": { "TorchPPOOptimizer.update": { "total": 246.1464150699885, "count": 22818, "self": 246.1464150699885 } } } } } } }, "trainer_threads": { "total": 1.424999936716631e-06, "count": 1, "self": 1.424999936716631e-06 }, "TrainerController._save_models": { "total": 0.12484165800015035, "count": 1, "self": 0.0018819560004885716, "children": { "RLTrainer._checkpoint": { "total": 0.12295970199966177, "count": 1, "self": 0.12295970199966177 } } } } } } }