| { |
| "name": "root", |
| "gauges": { |
| "Pyramids.Policy.Entropy.mean": { |
| "value": 0.1456783264875412, |
| "min": 0.13752226531505585, |
| "max": 1.4408445358276367, |
| "count": 100 |
| }, |
| "Pyramids.Policy.Entropy.sum": { |
| "value": 4368.01904296875, |
| "min": 4102.3037109375, |
| "max": 43709.4609375, |
| "count": 100 |
| }, |
| "Pyramids.Step.mean": { |
| "value": 2999961.0, |
| "min": 29952.0, |
| "max": 2999961.0, |
| "count": 100 |
| }, |
| "Pyramids.Step.sum": { |
| "value": 2999961.0, |
| "min": 29952.0, |
| "max": 2999961.0, |
| "count": 100 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
| "value": 0.8241613507270813, |
| "min": -0.10794008523225784, |
| "max": 0.900831401348114, |
| "count": 100 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
| "value": 250.5450439453125, |
| "min": -25.905620574951172, |
| "max": 280.1585693359375, |
| "count": 100 |
| }, |
| "Pyramids.Policy.RndValueEstimate.mean": { |
| "value": 0.009535823948681355, |
| "min": -0.017106682062149048, |
| "max": 0.3071017861366272, |
| "count": 100 |
| }, |
| "Pyramids.Policy.RndValueEstimate.sum": { |
| "value": 2.898890495300293, |
| "min": -5.063578128814697, |
| "max": 73.70442962646484, |
| "count": 100 |
| }, |
| "Pyramids.Losses.PolicyLoss.mean": { |
| "value": 0.06602280647105847, |
| "min": 0.06452826270307785, |
| "max": 0.07347443179132343, |
| "count": 100 |
| }, |
| "Pyramids.Losses.PolicyLoss.sum": { |
| "value": 0.9903420970658771, |
| "min": 0.4903758204205566, |
| "max": 1.0729813410822922, |
| "count": 100 |
| }, |
| "Pyramids.Losses.ValueLoss.mean": { |
| "value": 0.014181303273653611, |
| "min": 0.00018892298447589306, |
| "max": 0.017996830904545884, |
| "count": 100 |
| }, |
| "Pyramids.Losses.ValueLoss.sum": { |
| "value": 0.21271954910480417, |
| "min": 0.0024559987981866097, |
| "max": 0.2519556326636424, |
| "count": 100 |
| }, |
| "Pyramids.Policy.LearningRate.mean": { |
| "value": 1.5207728264422221e-06, |
| "min": 1.5207728264422221e-06, |
| "max": 0.00029838354339596195, |
| "count": 100 |
| }, |
| "Pyramids.Policy.LearningRate.sum": { |
| "value": 2.2811592396633334e-05, |
| "min": 2.2811592396633334e-05, |
| "max": 0.003969151576949499, |
| "count": 100 |
| }, |
| "Pyramids.Policy.Epsilon.mean": { |
| "value": 0.10050689111111111, |
| "min": 0.10050689111111111, |
| "max": 0.19946118095238097, |
| "count": 100 |
| }, |
| "Pyramids.Policy.Epsilon.sum": { |
| "value": 1.5076033666666666, |
| "min": 1.3962282666666668, |
| "max": 2.7674234, |
| "count": 100 |
| }, |
| "Pyramids.Policy.Beta.mean": { |
| "value": 6.063842200000001e-05, |
| "min": 6.063842200000001e-05, |
| "max": 0.009946171977142856, |
| "count": 100 |
| }, |
| "Pyramids.Policy.Beta.sum": { |
| "value": 0.0009095763300000001, |
| "min": 0.0009095763300000001, |
| "max": 0.13231274495, |
| "count": 100 |
| }, |
| "Pyramids.Losses.RNDLoss.mean": { |
| "value": 0.005344085860997438, |
| "min": 0.005344085860997438, |
| "max": 0.3970361649990082, |
| "count": 100 |
| }, |
| "Pyramids.Losses.RNDLoss.sum": { |
| "value": 0.08016128838062286, |
| "min": 0.07512924820184708, |
| "max": 2.7792532444000244, |
| "count": 100 |
| }, |
| "Pyramids.Environment.EpisodeLength.mean": { |
| "value": 219.44274809160305, |
| "min": 193.45945945945945, |
| "max": 999.0, |
| "count": 100 |
| }, |
| "Pyramids.Environment.EpisodeLength.sum": { |
| "value": 28747.0, |
| "min": 15984.0, |
| "max": 32466.0, |
| "count": 100 |
| }, |
| "Pyramids.Environment.CumulativeReward.mean": { |
| "value": 1.7652854870521386, |
| "min": -1.0000000521540642, |
| "max": 1.8063019953118076, |
| "count": 100 |
| }, |
| "Pyramids.Environment.CumulativeReward.sum": { |
| "value": 231.25239880383015, |
| "min": -30.998401626944542, |
| "max": 269.1389973014593, |
| "count": 100 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.mean": { |
| "value": 1.7652854870521386, |
| "min": -1.0000000521540642, |
| "max": 1.8063019953118076, |
| "count": 100 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.sum": { |
| "value": 231.25239880383015, |
| "min": -30.998401626944542, |
| "max": 269.1389973014593, |
| "count": 100 |
| }, |
| "Pyramids.Policy.RndReward.mean": { |
| "value": 0.012193113137496447, |
| "min": 0.011569673462121146, |
| "max": 7.741659015417099, |
| "count": 100 |
| }, |
| "Pyramids.Policy.RndReward.sum": { |
| "value": 1.5972978210120345, |
| "min": 1.5972978210120345, |
| "max": 123.86654424667358, |
| "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": "1791629038", |
| "python_version": "3.10.22 (main, Oct 1 2026, 15:39:47) [GCC 13.3.0]", |
| "command_line_arguments": "/content/mlagents_venv/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics --force", |
| "mlagents_version": "1.2.0.dev0", |
| "mlagents_envs_version": "1.2.0.dev0", |
| "communication_protocol_version": "1.5.0", |
| "pytorch_version": "2.8.0+cu128", |
| "numpy_version": "1.23.5", |
| "end_time_seconds": "1791636811" |
| }, |
| "total": 7772.758892688999, |
| "count": 1, |
| "self": 1.0632977260002008, |
| "children": { |
| "run_training.setup": { |
| "total": 0.019537340000169934, |
| "count": 1, |
| "self": 0.019537340000169934 |
| }, |
| "TrainerController.start_learning": { |
| "total": 7771.676057622999, |
| "count": 1, |
| "self": 4.023516981452303, |
| "children": { |
| "TrainerController._reset_env": { |
| "total": 3.3529986980001922, |
| "count": 1, |
| "self": 3.3529986980001922 |
| }, |
| "TrainerController.advance": { |
| "total": 7764.191427329548, |
| "count": 195497, |
| "self": 4.320858492525986, |
| "children": { |
| "env_step": { |
| "total": 5883.343904503117, |
| "count": 195497, |
| "self": 5438.988055617041, |
| "children": { |
| "SubprocessEnvManager._take_step": { |
| "total": 441.86197748912946, |
| "count": 195497, |
| "self": 14.124693193703024, |
| "children": { |
| "TorchPolicy.evaluate": { |
| "total": 427.73728429542643, |
| "count": 187561, |
| "self": 427.73728429542643 |
| } |
| } |
| }, |
| "workers": { |
| "total": 2.49387139694727, |
| "count": 195497, |
| "self": 0.0, |
| "children": { |
| "worker_root": { |
| "total": 7755.064610645825, |
| "count": 195497, |
| "is_parallel": true, |
| "self": 2667.854996796037, |
| "children": { |
| "run_training.setup": { |
| "total": 0.0, |
| "count": 0, |
| "is_parallel": true, |
| "self": 0.0, |
| "children": { |
| "steps_from_proto": { |
| "total": 0.005219912000029581, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0037296130003596772, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0014902989996699034, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.0014902989996699034 |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 0.09452404299963746, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0006444360001296445, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 0.00045319499986362644, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.00045319499986362644 |
| }, |
| "communicator.exchange": { |
| "total": 0.09150164899983793, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.09150164899983793 |
| }, |
| "steps_from_proto": { |
| "total": 0.001924762999806262, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.00037151399919821415, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.001553249000608048, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.001553249000608048 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 5087.209613849788, |
| "count": 195496, |
| "is_parallel": true, |
| "self": 99.68451313053083, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 67.87310431295464, |
| "count": 195496, |
| "is_parallel": true, |
| "self": 67.87310431295464 |
| }, |
| "communicator.exchange": { |
| "total": 4589.350732818053, |
| "count": 195496, |
| "is_parallel": true, |
| "self": 4589.350732818053 |
| }, |
| "steps_from_proto": { |
| "total": 330.30126358824964, |
| "count": 195496, |
| "is_parallel": true, |
| "self": 69.0620958672298, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 261.23916772101984, |
| "count": 1563968, |
| "is_parallel": true, |
| "self": 261.23916772101984 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_advance": { |
| "total": 1876.5266643339046, |
| "count": 195497, |
| "self": 8.06368940793027, |
| "children": { |
| "process_trajectory": { |
| "total": 345.59912891495424, |
| "count": 195497, |
| "self": 344.9411073489541, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.6580215660001159, |
| "count": 6, |
| "self": 0.6580215660001159 |
| } |
| } |
| }, |
| "_update_policy": { |
| "total": 1522.86384601102, |
| "count": 1395, |
| "self": 823.3000624820493, |
| "children": { |
| "TorchPPOOptimizer.update": { |
| "total": 699.5637835289708, |
| "count": 68403, |
| "self": 699.5637835289708 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_threads": { |
| "total": 1.1449992598500103e-06, |
| "count": 1, |
| "self": 1.1449992598500103e-06 |
| }, |
| "TrainerController._save_models": { |
| "total": 0.10811346899936325, |
| "count": 1, |
| "self": 0.00131035499907739, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.10680311400028586, |
| "count": 1, |
| "self": 0.10680311400028586 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
