{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5235576629638672, "min": 0.5086338520050049, "max": 1.471824288368225, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 15756.9921875, "min": 15259.015625, "max": 44649.26171875, "count": 33 }, "Pyramids.Step.mean": { "value": 989967.0, "min": 29879.0, "max": 989967.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989967.0, "min": 29879.0, "max": 989967.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.46829134225845337, "min": -0.1322522759437561, "max": 0.5012826323509216, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 125.50208282470703, "min": -31.34379005432129, "max": 137.85272216796875, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.02718088962137699, "min": 0.007172916084527969, "max": 0.6062001585960388, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 7.284478187561035, "min": 1.9079957008361816, "max": 143.66943359375, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06456502532195632, "min": 0.06456502532195632, "max": 0.07355335303111046, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9039103545073884, "min": 0.4990554301428807, "max": 1.0944907090115343, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.030393895399313243, "min": 4.955724833027785e-05, "max": 0.030393895399313243, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.4255145355903854, "min": 0.0006442442282936121, "max": 0.4255145355903854, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 2.5361597463849987e-05, "min": 2.5361597463849987e-05, "max": 0.0009841201444451284, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0003550623644938998, "min": 0.0003550623644938998, "max": 0.012026773097322703, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10253614999999996, "min": 0.10253614999999996, "max": 0.19841201428571426, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4355060999999996, "min": 1.3888840999999998, "max": 2.5696076999999997, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026336138499999997, "min": 0.00026336138499999997, "max": 0.009841360227142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036870593899999992, "min": 0.0036870593899999992, "max": 0.12027746227, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.0144507372751832, "min": 0.0144507372751832, "max": 0.6418731808662415, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.20231032371520996, "min": 0.20231032371520996, "max": 4.493112087249756, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 406.2972972972973, "min": 388.48, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30066.0, "min": 16678.0, "max": 33458.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.4357653145988782, "min": -0.9998200515906016, "max": 1.5562683261836632, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 107.68239859491587, "min": -29.994601547718048, "max": 122.94519776850939, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.4357653145988782, "min": -0.9998200515906016, "max": 1.5562683261836632, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 107.68239859491587, "min": -29.994601547718048, "max": 122.94519776850939, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.06058847799198702, "min": 0.06058847799198702, "max": 12.15372983322424, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.5441358493990265, "min": 4.471032229572302, "max": 206.6134071648121, "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": "1730783201", "python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn /content/ml-agents/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": "2.5.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1730785472" }, "total": 2271.340723722, "count": 1, "self": 0.44032952400038994, "children": { "run_training.setup": { "total": 0.11492714499991052, "count": 1, "self": 0.11492714499991052 }, "TrainerController.start_learning": { "total": 2270.7854670529996, "count": 1, "self": 1.4296400390885537, "children": { "TrainerController._reset_env": { "total": 3.7495636180001384, "count": 1, "self": 3.7495636180001384 }, "TrainerController.advance": { "total": 2265.523913978912, "count": 63683, "self": 1.4994117518417625, "children": { "env_step": { "total": 1552.9951192920425, "count": 63683, "self": 1393.615920595099, "children": { "SubprocessEnvManager._take_step": { "total": 158.4936713009456, "count": 63683, "self": 4.91421089798996, "children": { "TorchPolicy.evaluate": { "total": 153.57946040295565, "count": 62573, "self": 153.57946040295565 } } }, "workers": { "total": 0.8855273959979968, "count": 63683, "self": 0.0, "children": { "worker_root": { "total": 2265.316386705951, "count": 63683, "is_parallel": true, "self": 995.6431665069981, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004318263000186562, "count": 1, "is_parallel": true, "self": 0.002080732999729662, "children": { "_process_rank_one_or_two_observation": { "total": 0.0022375300004569, "count": 8, "is_parallel": true, "self": 0.0022375300004569 } } }, "UnityEnvironment.step": { "total": 0.056692501999805245, "count": 1, "is_parallel": true, "self": 0.0007164479998209572, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005009830001654336, "count": 1, "is_parallel": true, "self": 0.0005009830001654336 }, "communicator.exchange": { "total": 0.05361754099976679, "count": 1, "is_parallel": true, "self": 0.05361754099976679 }, "steps_from_proto": { "total": 0.0018575300000520656, "count": 1, "is_parallel": true, "self": 0.00040857500016500126, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014489549998870643, "count": 8, "is_parallel": true, "self": 0.0014489549998870643 } } } } } } }, "UnityEnvironment.step": { "total": 1269.673220198953, "count": 63682, "is_parallel": true, "self": 34.519384733991046, "children": { "UnityEnvironment._generate_step_input": { "total": 24.237258836918045, "count": 63682, "is_parallel": true, "self": 24.237258836918045 }, "communicator.exchange": { "total": 1107.7985341170397, "count": 63682, "is_parallel": true, "self": 1107.7985341170397 }, "steps_from_proto": { "total": 103.1180425110042, "count": 63682, "is_parallel": true, "self": 21.285903256972233, "children": { "_process_rank_one_or_two_observation": { "total": 81.83213925403197, "count": 509456, "is_parallel": true, "self": 81.83213925403197 } } } } } } } } } } }, "trainer_advance": { "total": 711.0293829350276, "count": 63683, "self": 2.770359816038308, "children": { "process_trajectory": { "total": 139.30413107699133, "count": 63683, "self": 139.0764808019917, "children": { "RLTrainer._checkpoint": { "total": 0.22765027499963253, "count": 2, "self": 0.22765027499963253 } } }, "_update_policy": { "total": 568.9548920419979, "count": 453, "self": 319.88969404503814, "children": { "TorchPPOOptimizer.update": { "total": 249.0651979969598, "count": 22752, "self": 249.0651979969598 } } } } } } }, "trainer_threads": { "total": 1.1089996405644342e-06, "count": 1, "self": 1.1089996405644342e-06 }, "TrainerController._save_models": { "total": 0.08234830799938209, "count": 1, "self": 0.002007665999371966, "children": { "RLTrainer._checkpoint": { "total": 0.08034064200001012, "count": 1, "self": 0.08034064200001012 } } } } } } }