{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.31008702516555786, "min": 0.31008702516555786, "max": 1.4250521659851074, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 9362.1474609375, "min": 9362.1474609375, "max": 43230.3828125, "count": 33 }, "Pyramids.Step.mean": { "value": 989872.0, "min": 29952.0, "max": 989872.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989872.0, "min": 29952.0, "max": 989872.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6640504598617554, "min": -0.07695551961660385, "max": 0.6657742857933044, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 191.2465362548828, "min": -18.546279907226562, "max": 191.2465362548828, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.006456466857343912, "min": -0.030368784442543983, "max": 0.4467553496360779, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -1.8594624996185303, "min": -8.837316513061523, "max": 105.88101959228516, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06622189611551307, "min": 0.0643686444952439, "max": 0.07202174772504528, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.927106545617183, "min": 0.492241782424289, "max": 1.053723674592238, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015477012580959125, "min": 0.0009020731691488943, "max": 0.01830905682870535, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21667817613342774, "min": 0.01262902436808452, "max": 0.2620538859337103, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.592197469300003e-06, "min": 7.592197469300003e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010629076457020004, "min": 0.00010629076457020004, "max": 0.0036335206888264996, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1025307, "min": 0.1025307, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4354298, "min": 1.3886848, "max": 2.6111735000000005, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002628169300000001, "min": 0.0002628169300000001, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036794370200000015, "min": 0.0036794370200000015, "max": 0.12113623265, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.014713114127516747, "min": 0.014713114127516747, "max": 0.6245303153991699, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.20598359405994415, "min": 0.20598359405994415, "max": 4.3717122077941895, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 283.41346153846155, "min": 275.24528301886795, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29475.0, "min": 15984.0, "max": 33183.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6973480662474265, "min": -1.0000000521540642, "max": 1.7247547054628156, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 176.52419888973236, "min": -30.56000167131424, "max": 187.46199874579906, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6973480662474265, "min": -1.0000000521540642, "max": 1.7247547054628156, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 176.52419888973236, "min": -30.56000167131424, "max": 187.46199874579906, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04266393794289168, "min": 0.04266393794289168, "max": 12.34556769952178, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.437049546060734, "min": 4.437049546060734, "max": 197.52908319234848, "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": "1786300866", "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": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1786303539" }, "total": 2673.1181676980004, "count": 1, "self": 0.528476313000283, "children": { "run_training.setup": { "total": 0.02714644500065333, "count": 1, "self": 0.02714644500065333 }, "TrainerController.start_learning": { "total": 2672.5625449399995, "count": 1, "self": 1.6210982538696044, "children": { "TrainerController._reset_env": { "total": 3.127874912999687, "count": 1, "self": 3.127874912999687 }, "TrainerController.advance": { "total": 2667.73569698713, "count": 64122, "self": 1.6189589381874612, "children": { "env_step": { "total": 1996.6259721980005, "count": 64122, "self": 1825.4110281259927, "children": { "SubprocessEnvManager._take_step": { "total": 170.26160575701397, "count": 64122, "self": 5.161752135050847, "children": { "TorchPolicy.evaluate": { "total": 165.09985362196312, "count": 62562, "self": 165.09985362196312 } } }, "workers": { "total": 0.9533383149937436, "count": 64122, "self": 0.0, "children": { "worker_root": { "total": 2666.630096849949, "count": 64122, "is_parallel": true, "self": 975.8592619279298, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.003394078999917838, "count": 1, "is_parallel": true, "self": 0.001232395999977598, "children": { "_process_rank_one_or_two_observation": { "total": 0.00216168299994024, "count": 8, "is_parallel": true, "self": 0.00216168299994024 } } }, "UnityEnvironment.step": { "total": 0.10277523999957339, "count": 1, "is_parallel": true, "self": 0.0026243629999953555, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004693159999078489, "count": 1, "is_parallel": true, "self": 0.0004693159999078489 }, "communicator.exchange": { "total": 0.09804659399924276, "count": 1, "is_parallel": true, "self": 0.09804659399924276 }, "steps_from_proto": { "total": 0.001634967000427423, "count": 1, "is_parallel": true, "self": 0.00034373400012555066, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012912330003018724, "count": 8, "is_parallel": true, "self": 0.0012912330003018724 } } } } } } }, "UnityEnvironment.step": { "total": 1690.7708349220193, "count": 64121, "is_parallel": true, "self": 37.4227404107196, "children": { "UnityEnvironment._generate_step_input": { "total": 26.05220636518243, "count": 64121, "is_parallel": true, "self": 26.05220636518243 }, "communicator.exchange": { "total": 1503.750106948186, "count": 64121, "is_parallel": true, "self": 1503.750106948186 }, "steps_from_proto": { "total": 123.54578119793132, "count": 64121, "is_parallel": true, "self": 25.61507074902056, "children": { "_process_rank_one_or_two_observation": { "total": 97.93071044891076, "count": 512968, "is_parallel": true, "self": 97.93071044891076 } } } } } } } } } } }, "trainer_advance": { "total": 669.4907658509419, "count": 64122, "self": 3.1631569458713784, "children": { "process_trajectory": { "total": 120.47406976806724, "count": 64122, "self": 120.168860901068, "children": { "RLTrainer._checkpoint": { "total": 0.3052088669992372, "count": 2, "self": 0.3052088669992372 } } }, "_update_policy": { "total": 545.8535391370033, "count": 452, "self": 294.8667472940251, "children": { "TorchPPOOptimizer.update": { "total": 250.98679184297816, "count": 22755, "self": 250.98679184297816 } } } } } } }, "trainer_threads": { "total": 1.0500007192604244e-06, "count": 1, "self": 1.0500007192604244e-06 }, "TrainerController._save_models": { "total": 0.07787373599967395, "count": 1, "self": 0.0010866149987123208, "children": { "RLTrainer._checkpoint": { "total": 0.07678712100096163, "count": 1, "self": 0.07678712100096163 } } } } } } }