{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3354620933532715, "min": 0.32278740406036377, "max": 1.496861219406128, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 9994.0869140625, "min": 9719.7744140625, "max": 45408.78125, "count": 33 }, "Pyramids.Step.mean": { "value": 989891.0, "min": 29988.0, "max": 989891.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989891.0, "min": 29988.0, "max": 989891.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.4248218238353729, "min": -0.09585706889629364, "max": 0.5357537865638733, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 114.27706909179688, "min": -23.00569725036621, "max": 148.93955993652344, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.023587722331285477, "min": 0.0006302906549535692, "max": 0.2846336364746094, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 6.345097541809082, "min": 0.1695481836795807, "max": 68.31207275390625, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06815364404060309, "min": 0.06653054570993612, "max": 0.0740278109052343, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9541510165684433, "min": 0.5096077540408166, "max": 1.0878230865731464, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016066689635546267, "min": 0.00016624153658229143, "max": 0.016066689635546267, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.22493365489764772, "min": 0.0021611399755697884, "max": 0.22493365489764772, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.721625997585712e-06, "min": 7.721625997585712e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010810276396619997, "min": 0.00010810276396619997, "max": 0.0036323722892093, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10257384285714287, "min": 0.10257384285714287, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4360338000000001, "min": 1.3886848, "max": 2.6107907000000004, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002671269014285714, "min": 0.0002671269014285714, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0037397766199999995, "min": 0.0037397766199999995, "max": 0.12109799093000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.007899695076048374, "min": 0.007899695076048374, "max": 0.45967555046081543, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.11059572547674179, "min": 0.11059572547674179, "max": 3.217728853225708, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 394.40845070422534, "min": 349.64285714285717, "max": 998.3548387096774, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28003.0, "min": 16787.0, "max": 33178.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.408360544644611, "min": -0.9347677956665715, "max": 1.5594607370940945, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 99.99359866976738, "min": -28.97780166566372, "max": 130.6273981332779, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.408360544644611, "min": -0.9347677956665715, "max": 1.5594607370940945, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 99.99359866976738, "min": -28.97780166566372, "max": 130.6273981332779, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03283301999703915, "min": 0.03144020907593585, "max": 8.560034616028561, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.33114441978978, "min": 2.33114441978978, "max": 145.52058847248554, "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": "1742830094", "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": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1742833348" }, "total": 3253.4820147150003, "count": 1, "self": 0.6452644940004575, "children": { "run_training.setup": { "total": 0.034740087000045605, "count": 1, "self": 0.034740087000045605 }, "TrainerController.start_learning": { "total": 3252.802010134, "count": 1, "self": 2.4073930570211814, "children": { "TrainerController._reset_env": { "total": 2.8404158389998884, "count": 1, "self": 2.8404158389998884 }, "TrainerController.advance": { "total": 3247.433237825979, "count": 63743, "self": 2.6170911138724477, "children": { "env_step": { "total": 2182.011996869005, "count": 63743, "self": 2019.1360712599815, "children": { "SubprocessEnvManager._take_step": { "total": 161.48922272405366, "count": 63743, "self": 7.324487857119266, "children": { "TorchPolicy.evaluate": { "total": 154.1647348669344, "count": 62558, "self": 154.1647348669344 } } }, "workers": { "total": 1.3867028849699636, "count": 63743, "self": 0.0, "children": { "worker_root": { "total": 3244.950369177994, "count": 63743, "is_parallel": true, "self": 1403.881363494922, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.003988553999988653, "count": 1, "is_parallel": true, "self": 0.0015630689995305147, "children": { "_process_rank_one_or_two_observation": { "total": 0.0024254850004581385, "count": 8, "is_parallel": true, "self": 0.0024254850004581385 } } }, "UnityEnvironment.step": { "total": 0.06492645799994534, "count": 1, "is_parallel": true, "self": 0.0006610620000628842, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004976789998636377, "count": 1, "is_parallel": true, "self": 0.0004976789998636377 }, "communicator.exchange": { "total": 0.06181605599999784, "count": 1, "is_parallel": true, "self": 0.06181605599999784 }, "steps_from_proto": { "total": 0.0019516610000209766, "count": 1, "is_parallel": true, "self": 0.0004276240001672704, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015240369998537062, "count": 8, "is_parallel": true, "self": 0.0015240369998537062 } } } } } } }, "UnityEnvironment.step": { "total": 1841.0690056830722, "count": 63742, "is_parallel": true, "self": 45.46816974008311, "children": { "UnityEnvironment._generate_step_input": { "total": 31.87008079004727, "count": 63742, "is_parallel": true, "self": 31.87008079004727 }, "communicator.exchange": { "total": 1637.3381557399846, "count": 63742, "is_parallel": true, "self": 1637.3381557399846 }, "steps_from_proto": { "total": 126.39259941295722, "count": 63742, "is_parallel": true, "self": 27.735217713014208, "children": { "_process_rank_one_or_two_observation": { "total": 98.65738169994302, "count": 509936, "is_parallel": true, "self": 98.65738169994302 } } } } } } } } } } }, "trainer_advance": { "total": 1062.8041498431016, "count": 63743, "self": 4.693009575050155, "children": { "process_trajectory": { "total": 161.0232611310562, "count": 63743, "self": 160.64313597105684, "children": { "RLTrainer._checkpoint": { "total": 0.38012515999935204, "count": 2, "self": 0.38012515999935204 } } }, "_update_policy": { "total": 897.0878791369953, "count": 456, "self": 358.1046665999768, "children": { "TorchPPOOptimizer.update": { "total": 538.9832125370185, "count": 22773, "self": 538.9832125370185 } } } } } } }, "trainer_threads": { "total": 1.8760001694317907e-06, "count": 1, "self": 1.8760001694317907e-06 }, "TrainerController._save_models": { "total": 0.12096153599941317, "count": 1, "self": 0.006353046999720391, "children": { "RLTrainer._checkpoint": { "total": 0.11460848899969278, "count": 1, "self": 0.11460848899969278 } } } } } } }