{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.40654268860816956, "min": 0.40654268860816956, "max": 1.5022521018981934, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 12280.841796875, "min": 12280.841796875, "max": 45572.3203125, "count": 33 }, "Pyramids.Step.mean": { "value": 989935.0, "min": 29952.0, "max": 989935.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989935.0, "min": 29952.0, "max": 989935.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6847007274627686, "min": -0.11671803891658783, "max": 0.6847007274627686, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 195.82440185546875, "min": -28.0123291015625, "max": 197.16989135742188, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.0036297061014920473, "min": -0.027422035112977028, "max": 0.2388150990009308, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 1.0380959510803223, "min": -7.979812145233154, "max": 57.554439544677734, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07216228049115411, "min": 0.06527683651567982, "max": 0.0746102561022927, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0102719268761575, "min": 0.5059808264907996, "max": 1.0592539993459449, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01520426227112434, "min": 0.0005237336938634318, "max": 0.01577473185499825, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21285967179574075, "min": 0.004713603244770887, "max": 0.22946904852869918, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.526711776842859e-06, "min": 7.526711776842859e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010537396487580002, "min": 0.00010537396487580002, "max": 0.0033829127723625, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10250887142857144, "min": 0.10250887142857144, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4351242000000002, "min": 1.3886848, "max": 2.5724362, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002606362557142858, "min": 0.0002606362557142858, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003648907580000001, "min": 0.003648907580000001, "max": 0.11279098625, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010599602945148945, "min": 0.010599602945148945, "max": 0.482708603143692, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.14839443564414978, "min": 0.14839443564414978, "max": 3.378960132598877, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 273.7037037037037, "min": 273.7037037037037, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29560.0, "min": 15984.0, "max": 33301.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7077740582602996, "min": -1.0000000521540642, "max": 1.7077740582602996, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 184.43959829211235, "min": -31.999601677060127, "max": 184.43959829211235, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7077740582602996, "min": -1.0000000521540642, "max": 1.7077740582602996, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 184.43959829211235, "min": -31.999601677060127, "max": 184.43959829211235, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.02995279811740922, "min": 0.02995279811740922, "max": 9.767425576224923, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.2349021966801956, "min": 3.2114742855046643, "max": 156.27880921959877, "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": "1694416024", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]", "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": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1694418449" }, "total": 2424.8385087690003, "count": 1, "self": 0.48889758599989364, "children": { "run_training.setup": { "total": 0.04076119999990624, "count": 1, "self": 0.04076119999990624 }, "TrainerController.start_learning": { "total": 2424.3088499830005, "count": 1, "self": 1.5510123779972673, "children": { "TrainerController._reset_env": { "total": 4.2169576270002835, "count": 1, "self": 4.2169576270002835 }, "TrainerController.advance": { "total": 2418.4237980150033, "count": 64139, "self": 1.4878473639951153, "children": { "env_step": { "total": 1720.8740822400146, "count": 64139, "self": 1604.0516270429184, "children": { "SubprocessEnvManager._take_step": { "total": 115.89471924915915, "count": 64139, "self": 5.078924882161118, "children": { "TorchPolicy.evaluate": { "total": 110.81579436699803, "count": 62564, "self": 110.81579436699803 } } }, "workers": { "total": 0.9277359479369807, "count": 64139, "self": 0.0, "children": { "worker_root": { "total": 2418.1898244679905, "count": 64139, "is_parallel": true, "self": 936.2946774650154, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018328349997318583, "count": 1, "is_parallel": true, "self": 0.0005092140004308021, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013236209993010561, "count": 8, "is_parallel": true, "self": 0.0013236209993010561 } } }, "UnityEnvironment.step": { "total": 0.047769027999947866, "count": 1, "is_parallel": true, "self": 0.0005974619998596609, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00046440400001301896, "count": 1, "is_parallel": true, "self": 0.00046440400001301896 }, "communicator.exchange": { "total": 0.04478285200002574, "count": 1, "is_parallel": true, "self": 0.04478285200002574 }, "steps_from_proto": { "total": 0.001924310000049445, "count": 1, "is_parallel": true, "self": 0.00035694799953489564, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015673620005145494, "count": 8, "is_parallel": true, "self": 0.0015673620005145494 } } } } } } }, "UnityEnvironment.step": { "total": 1481.8951470029751, "count": 64138, "is_parallel": true, "self": 36.038008971002455, "children": { "UnityEnvironment._generate_step_input": { "total": 23.76423257599936, "count": 64138, "is_parallel": true, "self": 23.76423257599936 }, "communicator.exchange": { "total": 1309.039509526051, "count": 64138, "is_parallel": true, "self": 1309.039509526051 }, "steps_from_proto": { "total": 113.05339592992232, "count": 64138, "is_parallel": true, "self": 22.435417298984703, "children": { "_process_rank_one_or_two_observation": { "total": 90.61797863093761, "count": 513104, "is_parallel": true, "self": 90.61797863093761 } } } } } } } } } } }, "trainer_advance": { "total": 696.0618684109936, "count": 64139, "self": 2.8153745639042427, "children": { "process_trajectory": { "total": 118.07750294907919, "count": 64139, "self": 117.85316038407927, "children": { "RLTrainer._checkpoint": { "total": 0.22434256499991534, "count": 2, "self": 0.22434256499991534 } } }, "_update_policy": { "total": 575.1689908980102, "count": 442, "self": 375.3053352810134, "children": { "TorchPPOOptimizer.update": { "total": 199.86365561699677, "count": 22842, "self": 199.86365561699677 } } } } } } }, "trainer_threads": { "total": 9.570003385306336e-07, "count": 1, "self": 9.570003385306336e-07 }, "TrainerController._save_models": { "total": 0.11708100599935278, "count": 1, "self": 0.001555203998577781, "children": { "RLTrainer._checkpoint": { "total": 0.115525802000775, "count": 1, "self": 0.115525802000775 } } } } } } }