{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.43144872784614563, "min": 0.4298742711544037, "max": 1.4268684387207031, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 12971.07421875, "min": 12923.740234375, "max": 43285.48046875, "count": 33 }, "Pyramids.Step.mean": { "value": 989968.0, "min": 29952.0, "max": 989968.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989968.0, "min": 29952.0, "max": 989968.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.4166901707649231, "min": -0.10670433193445206, "max": 0.4882936179637909, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 112.92303466796875, "min": -25.609039306640625, "max": 131.8392791748047, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.021608717739582062, "min": -0.01533901784569025, "max": 0.2852512001991272, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 5.855962753295898, "min": -4.141534805297852, "max": 67.60453796386719, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06835754887510356, "min": 0.06481934832949524, "max": 0.07231871584787898, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9570056842514498, "min": 0.470992604787254, "max": 1.077441838024385, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015455850262133891, "min": 0.0005255619297673248, "max": 0.015732500621149285, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21638190366987448, "min": 0.004308121299455424, "max": 0.22025500869609, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.316304704121426e-06, "min": 7.316304704121426e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010242826585769997, "min": 0.00010242826585769997, "max": 0.0031367507544164995, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10243873571428573, "min": 0.10243873571428573, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4341423000000002, "min": 1.3691136000000002, "max": 2.4018295000000003, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025362969785714285, "min": 0.00025362969785714285, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035508157699999997, "min": 0.0035508157699999997, "max": 0.10458379165, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.0072791618295013905, "min": 0.0071706948801875114, "max": 0.4216586947441101, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.10190826654434204, "min": 0.10038972645998001, "max": 2.951610803604126, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 399.49333333333334, "min": 395.7792207792208, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29962.0, "min": 15984.0, "max": 33258.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.413773311773936, "min": -1.0000000521540642, "max": 1.6004999728971405, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 106.0329983830452, "min": -32.000001668930054, "max": 121.63799794018269, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.413773311773936, "min": -1.0000000521540642, "max": 1.6004999728971405, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 106.0329983830452, "min": -32.000001668930054, "max": 121.63799794018269, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.02984853458086339, "min": 0.02984853458086339, "max": 8.42334857210517, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.2386400935647544, "min": 2.233071887771075, "max": 134.7735771536827, "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": "1790019228", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/content/mlagents310/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids_Unit5 --no-graphics", "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": "1790021614" }, "total": 2385.9849309559995, "count": 1, "self": 0.48159133899935114, "children": { "run_training.setup": { "total": 0.018377328000497073, "count": 1, "self": 0.018377328000497073 }, "TrainerController.start_learning": { "total": 2385.4849622889997, "count": 1, "self": 1.2852542749587883, "children": { "TrainerController._reset_env": { "total": 2.0717075350003142, "count": 1, "self": 2.0717075350003142 }, "TrainerController.advance": { "total": 2382.053030555041, "count": 63556, "self": 1.3934813070245582, "children": { "env_step": { "total": 1747.4567972940258, "count": 63556, "self": 1598.9045724342977, "children": { "SubprocessEnvManager._take_step": { "total": 147.77554347580372, "count": 63556, "self": 4.610679028660343, "children": { "TorchPolicy.evaluate": { "total": 143.16486444714337, "count": 62556, "self": 143.16486444714337 } } }, "workers": { "total": 0.7766813839243696, "count": 63556, "self": 0.0, "children": { "worker_root": { "total": 2378.2662964440306, "count": 63556, "is_parallel": true, "self": 899.1513808999471, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018446500007485156, "count": 1, "is_parallel": true, "self": 0.0006710260022373404, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011736239985111752, "count": 8, "is_parallel": true, "self": 0.0011736239985111752 } } }, "UnityEnvironment.step": { "total": 0.04699281600005634, "count": 1, "is_parallel": true, "self": 0.0005260050002107164, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004538570001386688, "count": 1, "is_parallel": true, "self": 0.0004538570001386688 }, "communicator.exchange": { "total": 0.0443450530001428, "count": 1, "is_parallel": true, "self": 0.0443450530001428 }, "steps_from_proto": { "total": 0.0016679009995641536, "count": 1, "is_parallel": true, "self": 0.0003673470009744051, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013005539985897485, "count": 8, "is_parallel": true, "self": 0.0013005539985897485 } } } } } } }, "UnityEnvironment.step": { "total": 1479.1149155440835, "count": 63555, "is_parallel": true, "self": 34.154791495711834, "children": { "UnityEnvironment._generate_step_input": { "total": 22.89126929518443, "count": 63555, "is_parallel": true, "self": 22.89126929518443 }, "communicator.exchange": { "total": 1309.0895844431461, "count": 63555, "is_parallel": true, "self": 1309.0895844431461 }, "steps_from_proto": { "total": 112.9792703100411, "count": 63555, "is_parallel": true, "self": 23.931421888732984, "children": { "_process_rank_one_or_two_observation": { "total": 89.04784842130812, "count": 508440, "is_parallel": true, "self": 89.04784842130812 } } } } } } } } } } }, "trainer_advance": { "total": 633.2027519539906, "count": 63556, "self": 2.474943951144269, "children": { "process_trajectory": { "total": 111.14468686284818, "count": 63556, "self": 110.96929824884774, "children": { "RLTrainer._checkpoint": { "total": 0.1753886140004397, "count": 2, "self": 0.1753886140004397 } } }, "_update_policy": { "total": 519.5831211399982, "count": 439, "self": 282.69948598595056, "children": { "TorchPPOOptimizer.update": { "total": 236.88363515404762, "count": 22866, "self": 236.88363515404762 } } } } } } }, "trainer_threads": { "total": 1.116999555961229e-06, "count": 1, "self": 1.116999555961229e-06 }, "TrainerController._save_models": { "total": 0.07496880700000474, "count": 1, "self": 0.0009582440006852266, "children": { "RLTrainer._checkpoint": { "total": 0.07401056299931952, "count": 1, "self": 0.07401056299931952 } } } } } } }