{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.6116529703140259, "min": 0.6061592102050781, "max": 1.3944107294082642, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 18339.802734375, "min": 18320.556640625, "max": 42300.84375, "count": 33 }, "Pyramids.Step.mean": { "value": 989975.0, "min": 29952.0, "max": 989975.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989975.0, "min": 29952.0, "max": 989975.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.33403143286705017, "min": -0.11313650012016296, "max": 0.40177735686302185, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 86.18010711669922, "min": -27.152759552001953, "max": 107.27455139160156, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.013097880408167839, "min": -0.04308406636118889, "max": 0.3253285586833954, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -3.3792531490325928, "min": -11.503445625305176, "max": 78.078857421875, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06867977549873536, "min": 0.06520782027610615, "max": 0.07517814151864355, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.961516856982295, "min": 0.4930097880163069, "max": 1.0359264655722369, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.011767660245823208, "min": 6.925681392715787e-05, "max": 0.01328377440998641, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.16474724344152492, "min": 0.0009003385810530523, "max": 0.19925661614979615, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.2890047132214335e-06, "min": 7.2890047132214335e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010204606598510007, "min": 0.00010204606598510007, "max": 0.0033317517894161, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10242963571428569, "min": 0.10242963571428569, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4340148999999998, "min": 1.3691136000000002, "max": 2.4430834999999997, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025272060785714304, "min": 0.00025272060785714304, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035380885100000023, "min": 0.0035380885100000023, "max": 0.11106733161000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009169643744826317, "min": 0.009169643744826317, "max": 0.4085240960121155, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.12837500870227814, "min": 0.12837500870227814, "max": 2.859668731689453, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 539.3962264150944, "min": 453.34285714285716, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28588.0, "min": 15984.0, "max": 32800.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.0816258972993604, "min": -1.0000000521540642, "max": 1.3184847183904405, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 58.40779845416546, "min": -32.000001668930054, "max": 89.03579786419868, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.0816258972993604, "min": -1.0000000521540642, "max": 1.3184847183904405, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 58.40779845416546, "min": -32.000001668930054, "max": 89.03579786419868, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.05281426646763942, "min": 0.04624830833802532, "max": 8.107680436223745, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.8519703892525285, "min": 2.8519703892525285, "max": 129.72288697957993, "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": "1704915982", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.2+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1704918133" }, "total": 2150.4950036, "count": 1, "self": 0.47779296200042154, "children": { "run_training.setup": { "total": 0.05154780199995912, "count": 1, "self": 0.05154780199995912 }, "TrainerController.start_learning": { "total": 2149.965662836, "count": 1, "self": 1.3095709379576874, "children": { "TrainerController._reset_env": { "total": 2.8784918490000564, "count": 1, "self": 2.8784918490000564 }, "TrainerController.advance": { "total": 2145.693191206042, "count": 63485, "self": 1.4609100699981354, "children": { "env_step": { "total": 1506.1341400329957, "count": 63485, "self": 1377.4946018808655, "children": { "SubprocessEnvManager._take_step": { "total": 127.80377161902743, "count": 63485, "self": 4.630873852981495, "children": { "TorchPolicy.evaluate": { "total": 123.17289776604593, "count": 62568, "self": 123.17289776604593 } } }, "workers": { "total": 0.835766533102742, "count": 63485, "self": 0.0, "children": { "worker_root": { "total": 2145.0528999210155, "count": 63485, "is_parallel": true, "self": 884.8097471549979, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002271119999932125, "count": 1, "is_parallel": true, "self": 0.0006082789998345106, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016628410000976146, "count": 8, "is_parallel": true, "self": 0.0016628410000976146 } } }, "UnityEnvironment.step": { "total": 0.08595335400013937, "count": 1, "is_parallel": true, "self": 0.0006425349999972241, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004172520000338409, "count": 1, "is_parallel": true, "self": 0.0004172520000338409 }, "communicator.exchange": { "total": 0.08312986800001454, "count": 1, "is_parallel": true, "self": 0.08312986800001454 }, "steps_from_proto": { "total": 0.0017636990000937658, "count": 1, "is_parallel": true, "self": 0.0003620420000061131, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014016570000876527, "count": 8, "is_parallel": true, "self": 0.0014016570000876527 } } } } } } }, "UnityEnvironment.step": { "total": 1260.2431527660176, "count": 63484, "is_parallel": true, "self": 34.6561118289078, "children": { "UnityEnvironment._generate_step_input": { "total": 24.146154590015612, "count": 63484, "is_parallel": true, "self": 24.146154590015612 }, "communicator.exchange": { "total": 1104.5051646560983, "count": 63484, "is_parallel": true, "self": 1104.5051646560983 }, "steps_from_proto": { "total": 96.93572169099593, "count": 63484, "is_parallel": true, "self": 19.135609518872798, "children": { "_process_rank_one_or_two_observation": { "total": 77.80011217212314, "count": 507872, "is_parallel": true, "self": 77.80011217212314 } } } } } } } } } } }, "trainer_advance": { "total": 638.0981411030482, "count": 63485, "self": 2.4847003570605466, "children": { "process_trajectory": { "total": 125.06147663298748, "count": 63485, "self": 124.87426974898722, "children": { "RLTrainer._checkpoint": { "total": 0.1872068840002612, "count": 2, "self": 0.1872068840002612 } } }, "_update_policy": { "total": 510.55196411300017, "count": 442, "self": 304.9086849919977, "children": { "TorchPPOOptimizer.update": { "total": 205.64327912100248, "count": 22770, "self": 205.64327912100248 } } } } } } }, "trainer_threads": { "total": 8.890001481631771e-07, "count": 1, "self": 8.890001481631771e-07 }, "TrainerController._save_models": { "total": 0.08440795400019852, "count": 1, "self": 0.0013986420003675448, "children": { "RLTrainer._checkpoint": { "total": 0.08300931199983097, "count": 1, "self": 0.08300931199983097 } } } } } } }