{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.49734601378440857, "min": 0.4790073335170746, "max": 1.3264129161834717, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 14960.16796875, "min": 14331.8994140625, "max": 40238.0625, "count": 33 }, "Pyramids.Step.mean": { "value": 989875.0, "min": 29937.0, "max": 989875.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989875.0, "min": 29937.0, "max": 989875.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5065950751304626, "min": -0.11977048218250275, "max": 0.5623494386672974, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 140.32684326171875, "min": -28.744915008544922, "max": 156.33314514160156, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.029130082577466965, "min": -0.039908889681100845, "max": 0.4272623062133789, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 8.069032669067383, "min": -10.935035705566406, "max": 101.26116943359375, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07173537374311469, "min": 0.06485745379713856, "max": 0.07504258903661845, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0042952324036056, "min": 0.5810198251213718, "max": 1.1256388355492768, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01669291511323699, "min": 0.00047593139434515356, "max": 0.017830996445740648, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.23370081158531783, "min": 0.00666303952083215, "max": 0.24963395024036908, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.401033247307141e-06, "min": 7.401033247307141e-06, "max": 0.0002948416892194375, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010361446546229997, "min": 0.00010361446546229997, "max": 0.003634496588501199, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10246697857142857, "min": 0.10246697857142857, "max": 0.19828056250000003, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4345377, "min": 1.4345377, "max": 2.6114988000000006, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025645115928571427, "min": 0.00025645115928571427, "max": 0.00982822819375, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035903162299999996, "min": 0.0035903162299999996, "max": 0.12116873012000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010068242438137531, "min": 0.010068242438137531, "max": 0.49813413619995117, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.14095538854599, "min": 0.14095538854599, "max": 3.9850730895996094, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 352.04819277108436, "min": 338.35632183908046, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29220.0, "min": 16480.0, "max": 33558.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5997517915016197, "min": -0.999962551984936, "max": 1.6277441670901553, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 132.77939869463444, "min": -31.998801663517952, "max": 140.56179805845022, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5997517915016197, "min": -0.999962551984936, "max": 1.6277441670901553, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 132.77939869463444, "min": -31.998801663517952, "max": 140.56179805845022, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03668121975027474, "min": 0.03668121975027474, "max": 9.720678557367886, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.044541239272803, "min": 3.044541239272803, "max": 165.25153547525406, "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": "1727349601", "python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [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": "2.4.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1727353088" }, "total": 3487.5913884389997, "count": 1, "self": 0.6509908139992149, "children": { "run_training.setup": { "total": 0.08190917499996431, "count": 1, "self": 0.08190917499996431 }, "TrainerController.start_learning": { "total": 3486.8584884500006, "count": 1, "self": 2.4270497010434156, "children": { "TrainerController._reset_env": { "total": 2.5115042249999533, "count": 1, "self": 2.5115042249999533 }, "TrainerController.advance": { "total": 3481.8374700359577, "count": 63716, "self": 2.5243765679938406, "children": { "env_step": { "total": 2327.432728138924, "count": 63716, "self": 2155.217982371914, "children": { "SubprocessEnvManager._take_step": { "total": 170.77722702199299, "count": 63716, "self": 7.4168800718452985, "children": { "TorchPolicy.evaluate": { "total": 163.3603469501477, "count": 62566, "self": 163.3603469501477 } } }, "workers": { "total": 1.4375187450173144, "count": 63716, "self": 0.0, "children": { "worker_root": { "total": 3478.8467117769046, "count": 63716, "is_parallel": true, "self": 1516.0120233359617, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.003494481999950949, "count": 1, "is_parallel": true, "self": 0.0013336530005290115, "children": { "_process_rank_one_or_two_observation": { "total": 0.0021608289994219376, "count": 8, "is_parallel": true, "self": 0.0021608289994219376 } } }, "UnityEnvironment.step": { "total": 0.06367670800000269, "count": 1, "is_parallel": true, "self": 0.0008998499997687759, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005558069997277926, "count": 1, "is_parallel": true, "self": 0.0005558069997277926 }, "communicator.exchange": { "total": 0.06013900600009947, "count": 1, "is_parallel": true, "self": 0.06013900600009947 }, "steps_from_proto": { "total": 0.0020820450004066515, "count": 1, "is_parallel": true, "self": 0.00045236900041345507, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016296759999931965, "count": 8, "is_parallel": true, "self": 0.0016296759999931965 } } } } } } }, "UnityEnvironment.step": { "total": 1962.834688440943, "count": 63715, "is_parallel": true, "self": 51.3737137449134, "children": { "UnityEnvironment._generate_step_input": { "total": 31.976054763074444, "count": 63715, "is_parallel": true, "self": 31.976054763074444 }, "communicator.exchange": { "total": 1746.5580799419095, "count": 63715, "is_parallel": true, "self": 1746.5580799419095 }, "steps_from_proto": { "total": 132.92683999104565, "count": 63715, "is_parallel": true, "self": 29.054715782005587, "children": { "_process_rank_one_or_two_observation": { "total": 103.87212420904007, "count": 509720, "is_parallel": true, "self": 103.87212420904007 } } } } } } } } } } }, "trainer_advance": { "total": 1151.8803653290397, "count": 63716, "self": 4.622221589957007, "children": { "process_trajectory": { "total": 175.45043482209485, "count": 63716, "self": 175.27301135709467, "children": { "RLTrainer._checkpoint": { "total": 0.17742346500017447, "count": 2, "self": 0.17742346500017447 } } }, "_update_policy": { "total": 971.8077089169878, "count": 455, "self": 387.2976176189777, "children": { "TorchPPOOptimizer.update": { "total": 584.5100912980101, "count": 22830, "self": 584.5100912980101 } } } } } } }, "trainer_threads": { "total": 1.1069996617152356e-06, "count": 1, "self": 1.1069996617152356e-06 }, "TrainerController._save_models": { "total": 0.08246338099979766, "count": 1, "self": 0.0021492160003617755, "children": { "RLTrainer._checkpoint": { "total": 0.08031416499943589, "count": 1, "self": 0.08031416499943589 } } } } } } }