{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3598211109638214, "min": 0.3598211109638214, "max": 1.408104419708252, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 10880.990234375, "min": 10880.990234375, "max": 42716.25390625, "count": 33 }, "Pyramids.Step.mean": { "value": 989963.0, "min": 29952.0, "max": 989963.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989963.0, "min": 29952.0, "max": 989963.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5877289175987244, "min": -0.10048624873161316, "max": 0.6369127035140991, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 162.8009033203125, "min": -24.11669921875, "max": 180.88320922851562, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.03193480148911476, "min": 3.044266668439377e-05, "max": 0.37435030937194824, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 8.845939636230469, "min": 0.007823765277862549, "max": 88.72102355957031, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07016587209363935, "min": 0.06566471407775792, "max": 0.07283612496530749, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9823222093109508, "min": 0.48839078375941875, "max": 1.0470493387050845, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016231858699549257, "min": 0.0007526604380795057, "max": 0.01635567372709158, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2272460217936896, "min": 0.009784585695033574, "max": 0.2289794321792821, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.368354686771426e-06, "min": 7.368354686771426e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010315696561479997, "min": 0.00010315696561479997, "max": 0.0033774274741908993, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10245608571428574, "min": 0.10245608571428574, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4343852000000004, "min": 1.3886848, "max": 2.5278750999999997, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025536296285714284, "min": 0.00025536296285714284, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035750814799999997, "min": 0.0035750814799999997, "max": 0.11259832909000002, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009957830421626568, "min": 0.009946039877831936, "max": 0.3796137869358063, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1394096314907074, "min": 0.13924455642700195, "max": 2.6572964191436768, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 327.05555555555554, "min": 292.6736842105263, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29435.0, "min": 15984.0, "max": 33331.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.628486644062731, "min": -1.0000000521540642, "max": 1.702437489759177, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 146.5637979656458, "min": -30.23300165683031, "max": 164.1105981618166, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.628486644062731, "min": -1.0000000521540642, "max": 1.702437489759177, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 146.5637979656458, "min": -30.23300165683031, "max": 164.1105981618166, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03342239633837178, "min": 0.030726387458950438, "max": 8.224931942299008, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.00801567045346, "min": 2.949733196059242, "max": 131.59891107678413, "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": "1792593716", "python_version": "3.10.12 (main, Jul 26 2023, 13:20:36) [Clang 16.0.3 ]", "command_line_arguments": "/content/unity-env/bin/mlagents-learn /content/unity-core/config/PyramidsRND.yaml --env=/content/unity-core/envs/Pyramids/Pyramids --run-id=Pyramids-core --results-dir=/content/unity-core/results --no-graphics --torch-device=cpu --seed=42", "mlagents_version": "1.1.0", "mlagents_envs_version": "1.1.0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.1+cpu", "numpy_version": "1.23.5", "end_time_seconds": "1792611340" }, "total": 17623.610679587997, "count": 1, "self": 2.7952866059968073, "children": { "run_training.setup": { "total": 0.1913546440000573, "count": 1, "self": 0.1913546440000573 }, "TrainerController.start_learning": { "total": 17620.624038338, "count": 1, "self": 9.820848370967724, "children": { "TrainerController._reset_env": { "total": 18.885466861999703, "count": 1, "self": 18.885466861999703 }, "TrainerController.advance": { "total": 17591.79000244103, "count": 63955, "self": 10.602275146087777, "children": { "env_step": { "total": 13978.780782688675, "count": 63955, "self": 13496.763965520498, "children": { "SubprocessEnvManager._take_step": { "total": 478.7557722063557, "count": 63955, "self": 27.035630163301903, "children": { "TorchPolicy.evaluate": { "total": 451.7201420430538, "count": 62564, "self": 451.7201420430538 } } }, "workers": { "total": 3.261044961821426, "count": 63955, "self": 0.0, "children": { "worker_root": { "total": 17552.917220717925, "count": 63955, "is_parallel": true, "self": 4687.897509987646, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.011928063000596012, "count": 1, "is_parallel": true, "self": 0.00552247900122893, "children": { "_process_rank_one_or_two_observation": { "total": 0.0064055839993670816, "count": 8, "is_parallel": true, "self": 0.0064055839993670816 } } }, "UnityEnvironment.step": { "total": 0.14682532500046364, "count": 1, "is_parallel": true, "self": 0.000680226000440598, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0006510889998025959, "count": 1, "is_parallel": true, "self": 0.0006510889998025959 }, "communicator.exchange": { "total": 0.14132261000031576, "count": 1, "is_parallel": true, "self": 0.14132261000031576 }, "steps_from_proto": { "total": 0.004171399999904679, "count": 1, "is_parallel": true, "self": 0.0004581599996527075, "children": { "_process_rank_one_or_two_observation": { "total": 0.0037132400002519717, "count": 8, "is_parallel": true, "self": 0.0037132400002519717 } } } } } } }, "UnityEnvironment.step": { "total": 12865.01971073028, "count": 63954, "is_parallel": true, "self": 98.99624691999088, "children": { "UnityEnvironment._generate_step_input": { "total": 52.47966483435903, "count": 63954, "is_parallel": true, "self": 52.47966483435903 }, "communicator.exchange": { "total": 12274.26954981107, "count": 63954, "is_parallel": true, "self": 12274.26954981107 }, "steps_from_proto": { "total": 439.2742491648605, "count": 63954, "is_parallel": true, "self": 79.98435607600095, "children": { "_process_rank_one_or_two_observation": { "total": 359.28989308885957, "count": 511632, "is_parallel": true, "self": 359.28989308885957 } } } } } } } } } } }, "trainer_advance": { "total": 3602.406944606266, "count": 63955, "self": 15.82441535403268, "children": { "process_trajectory": { "total": 574.9044073912291, "count": 63955, "self": 572.4615476922327, "children": { "RLTrainer._checkpoint": { "total": 2.4428596989964717, "count": 10, "self": 2.4428596989964717 } } }, "_update_policy": { "total": 3011.678121861004, "count": 450, "self": 1345.5544664201889, "children": { "TorchPPOOptimizer.update": { "total": 1666.1236554408151, "count": 22854, "self": 1666.1236554408151 } } } } } } }, "trainer_threads": { "total": 2.077002136502415e-06, "count": 1, "self": 2.077002136502415e-06 }, "TrainerController._save_models": { "total": 0.127718586998526, "count": 1, "self": 0.0037435240010381676, "children": { "RLTrainer._checkpoint": { "total": 0.12397506299748784, "count": 1, "self": 0.12397506299748784 } } } } } } }