{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4918648600578308, "min": 0.4918648600578308, "max": 1.472496509552002, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 14661.5078125, "min": 14661.5078125, "max": 44669.65234375, "count": 33 }, "Pyramids.Step.mean": { "value": 989878.0, "min": 29952.0, "max": 989878.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989878.0, "min": 29952.0, "max": 989878.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.21501803398132324, "min": -0.10819876194000244, "max": 0.3403164744377136, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 54.39956283569336, "min": -26.07590103149414, "max": 87.80165100097656, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.006905943620949984, "min": -0.03808030113577843, "max": 0.05363503098487854, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 1.7472037076950073, "min": -9.520074844360352, "max": 12.926042556762695, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06911271545760131, "min": 0.06091887155100411, "max": 0.07247982541541062, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9675780164064183, "min": 0.49829920096926383, "max": 1.0469261228087512, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.010311447635221025, "min": 0.00034951855390376096, "max": 0.012614916255427766, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.14436026689309434, "min": 0.004543741200748893, "max": 0.17660882757598872, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.685411723942859e-06, "min": 7.685411723942859e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010759576413520002, "min": 0.00010759576413520002, "max": 0.0033761512746162997, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10256177142857144, "min": 0.10256177142857144, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4358648, "min": 1.3886848, "max": 2.4253837000000003, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002659209657142858, "min": 0.0002659209657142858, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0037228935200000006, "min": 0.0037228935200000006, "max": 0.11255583163000002, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009169014170765877, "min": 0.008785725571215153, "max": 0.22358380258083344, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.12836620211601257, "min": 0.12390249222517014, "max": 1.5650866031646729, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 654.7391304347826, "min": 514.1272727272727, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30118.0, "min": 15984.0, "max": 32359.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.8233651901068895, "min": -1.0000000521540642, "max": 1.2329249790470516, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 37.874798744916916, "min": -30.260001629590988, "max": 69.04379882663488, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.8233651901068895, "min": -1.0000000521540642, "max": 1.2329249790470516, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 37.874798744916916, "min": -30.260001629590988, "max": 69.04379882663488, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.06280911366775399, "min": 0.04967818662147953, "max": 5.181517615914345, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.8892192287166836, "min": 2.617512088007061, "max": 82.90428185462952, "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": "1740278399", "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": "1740280617" }, "total": 2217.888209089, "count": 1, "self": 0.4877483300001586, "children": { "run_training.setup": { "total": 0.021597989999918354, "count": 1, "self": 0.021597989999918354 }, "TrainerController.start_learning": { "total": 2217.378862769, "count": 1, "self": 1.349649126955228, "children": { "TrainerController._reset_env": { "total": 2.729297740999982, "count": 1, "self": 2.729297740999982 }, "TrainerController.advance": { "total": 2213.204841660045, "count": 63356, "self": 1.4580236540627993, "children": { "env_step": { "total": 1536.1341472100512, "count": 63356, "self": 1378.540254067045, "children": { "SubprocessEnvManager._take_step": { "total": 156.80327432705076, "count": 63356, "self": 4.7712816460045815, "children": { "TorchPolicy.evaluate": { "total": 152.03199268104618, "count": 62568, "self": 152.03199268104618 } } }, "workers": { "total": 0.7906188159554404, "count": 63356, "self": 0.0, "children": { "worker_root": { "total": 2212.33750645606, "count": 63356, "is_parallel": true, "self": 945.7078903730601, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002474361000167846, "count": 1, "is_parallel": true, "self": 0.0007019540003057045, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017724069998621417, "count": 8, "is_parallel": true, "self": 0.0017724069998621417 } } }, "UnityEnvironment.step": { "total": 0.08311290899996493, "count": 1, "is_parallel": true, "self": 0.000540854000064428, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00042226000005030073, "count": 1, "is_parallel": true, "self": 0.00042226000005030073 }, "communicator.exchange": { "total": 0.08046750499988775, "count": 1, "is_parallel": true, "self": 0.08046750499988775 }, "steps_from_proto": { "total": 0.0016822899999624497, "count": 1, "is_parallel": true, "self": 0.0003603830000429298, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013219069999195199, "count": 8, "is_parallel": true, "self": 0.0013219069999195199 } } } } } } }, "UnityEnvironment.step": { "total": 1266.629616083, "count": 63355, "is_parallel": true, "self": 31.10217069198552, "children": { "UnityEnvironment._generate_step_input": { "total": 23.086398218965996, "count": 63355, "is_parallel": true, "self": 23.086398218965996 }, "communicator.exchange": { "total": 1116.4700419270218, "count": 63355, "is_parallel": true, "self": 1116.4700419270218 }, "steps_from_proto": { "total": 95.97100524502662, "count": 63355, "is_parallel": true, "self": 19.602799986098944, "children": { "_process_rank_one_or_two_observation": { "total": 76.36820525892767, "count": 506840, "is_parallel": true, "self": 76.36820525892767 } } } } } } } } } } }, "trainer_advance": { "total": 675.6126707959309, "count": 63356, "self": 2.5572727070280052, "children": { "process_trajectory": { "total": 126.01283364390133, "count": 63356, "self": 125.81075853490142, "children": { "RLTrainer._checkpoint": { "total": 0.20207510899990666, "count": 2, "self": 0.20207510899990666 } } }, "_update_policy": { "total": 547.0425644450015, "count": 442, "self": 300.6203574320259, "children": { "TorchPPOOptimizer.update": { "total": 246.4222070129756, "count": 22770, "self": 246.4222070129756 } } } } } } }, "trainer_threads": { "total": 7.989997357071843e-07, "count": 1, "self": 7.989997357071843e-07 }, "TrainerController._save_models": { "total": 0.09507344199982981, "count": 1, "self": 0.0014438369998970302, "children": { "RLTrainer._checkpoint": { "total": 0.09362960499993278, "count": 1, "self": 0.09362960499993278 } } } } } } }