{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4580756723880768, "min": 0.44120925664901733, "max": 1.438901662826538, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 13837.5498046875, "min": 13148.826171875, "max": 43650.51953125, "count": 33 }, "Pyramids.Step.mean": { "value": 989983.0, "min": 29952.0, "max": 989983.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989983.0, "min": 29952.0, "max": 989983.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6157048344612122, "min": -0.11506661027669907, "max": 0.6157048344612122, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 174.24447631835938, "min": -27.615985870361328, "max": 174.24447631835938, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.06109917163848877, "min": -0.009336709976196289, "max": 0.4564453065395355, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 17.291065216064453, "min": -2.614278793334961, "max": 108.17753601074219, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06723514862047722, "min": 0.06515462616288678, "max": 0.0737060114723859, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.941292080686681, "min": 0.4933924031256225, "max": 1.096493538636566, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.017911442783304112, "min": 0.0002828299259792338, "max": 0.017911442783304112, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.25076019896625756, "min": 0.002545469333813104, "max": 0.2579808210179109, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.358904689921432e-06, "min": 7.358904689921432e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010302466565890004, "min": 0.00010302466565890004, "max": 0.0032595575134808995, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10245293571428571, "min": 0.10245293571428571, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4343411, "min": 1.3886848, "max": 2.4432309000000005, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025504827785714296, "min": 0.00025504827785714296, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003570675890000002, "min": 0.003570675890000002, "max": 0.10867325809, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.015960926190018654, "min": 0.014975854195654392, "max": 0.5207635760307312, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.22345295548439026, "min": 0.20966196060180664, "max": 3.6453449726104736, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 308.3440860215054, "min": 308.3440860215054, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28676.0, "min": 15984.0, "max": 33191.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.648627935237782, "min": -1.0000000521540642, "max": 1.6791685193442227, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 153.32239797711372, "min": -31.99920167028904, "max": 153.32239797711372, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.648627935237782, "min": -1.0000000521540642, "max": 1.6791685193442227, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 153.32239797711372, "min": -31.99920167028904, "max": 153.32239797711372, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.05054460073475756, "min": 0.05054460073475756, "max": 10.648665897548199, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.700647868332453, "min": 4.623703599936562, "max": 170.37865436077118, "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": "1747208849", "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 --force", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.7.0+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1747211944" }, "total": 3095.4462897380004, "count": 1, "self": 1.4857556020006086, "children": { "run_training.setup": { "total": 0.02582167299988214, "count": 1, "self": 0.02582167299988214 }, "TrainerController.start_learning": { "total": 3093.934712463, "count": 1, "self": 2.3502924149311184, "children": { "TrainerController._reset_env": { "total": 2.465546287000052, "count": 1, "self": 2.465546287000052 }, "TrainerController.advance": { "total": 3088.995765018069, "count": 63716, "self": 2.5559743731005256, "children": { "env_step": { "total": 2063.0239034249944, "count": 63716, "self": 1905.7644886410676, "children": { "SubprocessEnvManager._take_step": { "total": 155.91910287592964, "count": 63716, "self": 7.217021466860388, "children": { "TorchPolicy.evaluate": { "total": 148.70208140906925, "count": 62582, "self": 148.70208140906925 } } }, "workers": { "total": 1.3403119079971475, "count": 63716, "self": 0.0, "children": { "worker_root": { "total": 3086.222237301982, "count": 63716, "is_parallel": true, "self": 1354.4830314230446, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0021879490000173973, "count": 1, "is_parallel": true, "self": 0.0006809799992879562, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015069690007294412, "count": 8, "is_parallel": true, "self": 0.0015069690007294412 } } }, "UnityEnvironment.step": { "total": 0.06642223900007593, "count": 1, "is_parallel": true, "self": 0.0006655560000581318, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005351960001007683, "count": 1, "is_parallel": true, "self": 0.0005351960001007683 }, "communicator.exchange": { "total": 0.06330523099995844, "count": 1, "is_parallel": true, "self": 0.06330523099995844 }, "steps_from_proto": { "total": 0.0019162559999585937, "count": 1, "is_parallel": true, "self": 0.0004089939993718872, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015072620005867066, "count": 8, "is_parallel": true, "self": 0.0015072620005867066 } } } } } } }, "UnityEnvironment.step": { "total": 1731.7392058789376, "count": 63715, "is_parallel": true, "self": 43.724836966902785, "children": { "UnityEnvironment._generate_step_input": { "total": 30.310057028048277, "count": 63715, "is_parallel": true, "self": 30.310057028048277 }, "communicator.exchange": { "total": 1535.2885523430077, "count": 63715, "is_parallel": true, "self": 1535.2885523430077 }, "steps_from_proto": { "total": 122.4157595409788, "count": 63715, "is_parallel": true, "self": 26.909040252955265, "children": { "_process_rank_one_or_two_observation": { "total": 95.50671928802353, "count": 509720, "is_parallel": true, "self": 95.50671928802353 } } } } } } } } } } }, "trainer_advance": { "total": 1023.4158872199741, "count": 63716, "self": 4.366050629054143, "children": { "process_trajectory": { "total": 157.69043367093468, "count": 63716, "self": 157.35465097493466, "children": { "RLTrainer._checkpoint": { "total": 0.33578269600002386, "count": 2, "self": 0.33578269600002386 } } }, "_update_policy": { "total": 861.3594029199853, "count": 441, "self": 346.5872196079781, "children": { "TorchPPOOptimizer.update": { "total": 514.7721833120072, "count": 22827, "self": 514.7721833120072 } } } } } } }, "trainer_threads": { "total": 1.794999661797192e-06, "count": 1, "self": 1.794999661797192e-06 }, "TrainerController._save_models": { "total": 0.123106947999986, "count": 1, "self": 0.006998925000516465, "children": { "RLTrainer._checkpoint": { "total": 0.11610802299946954, "count": 1, "self": 0.11610802299946954 } } } } } } }