{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4012230634689331, "min": 0.38882139325141907, "max": 1.3915460109710693, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 12011.013671875, "min": 11689.662109375, "max": 42213.94140625, "count": 33 }, "Pyramids.Step.mean": { "value": 989936.0, "min": 29952.0, "max": 989936.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989936.0, "min": 29952.0, "max": 989936.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6269130706787109, "min": -0.07648507505655289, "max": 0.6269130706787109, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 178.04331970214844, "min": -18.432903289794922, "max": 178.04331970214844, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.0006848539924249053, "min": -0.02524637058377266, "max": 0.5005385279655457, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 0.19449853897094727, "min": -6.665041923522949, "max": 118.62762451171875, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06549766080635083, "min": 0.06399838118685035, "max": 0.07307493575736587, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9824649120952624, "min": 0.49871460198181894, "max": 1.0921134987546988, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014147582980028042, "min": 0.0006362919493185139, "max": 0.018004458422089146, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21221374470042062, "min": 0.008908087290459193, "max": 0.24051189550664276, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.456837514420003e-06, "min": 7.456837514420003e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011185256271630004, "min": 0.00011185256271630004, "max": 0.0035081180306273997, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10248557999999999, "min": 0.10248557999999999, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5372837, "min": 1.3886848, "max": 2.5693726000000003, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025830944200000005, "min": 0.00025830944200000005, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003874641630000001, "min": 0.003874641630000001, "max": 0.11696032273999998, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009987115859985352, "min": 0.009987115859985352, "max": 0.6365255117416382, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.14980673789978027, "min": 0.1403665393590927, "max": 4.455678462982178, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 324.3645833333333, "min": 302.18390804597703, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31139.0, "min": 15984.0, "max": 33481.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6127810413900174, "min": -1.0000000521540642, "max": 1.6765408910472284, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 153.21419893205166, "min": -29.7412016838789, "max": 158.5165982618928, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6127810413900174, "min": -1.0000000521540642, "max": 1.6765408910472284, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 153.21419893205166, "min": -29.7412016838789, "max": 158.5165982618928, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03340763466349975, "min": 0.033007459157653844, "max": 14.277171859517694, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.1737252930324757, "min": 2.9046564058735385, "max": 228.4347497522831, "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": "1691758483", "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": "1691760922" }, "total": 2439.447275641999, "count": 1, "self": 0.9483664049994331, "children": { "run_training.setup": { "total": 0.04048803699970449, "count": 1, "self": 0.04048803699970449 }, "TrainerController.start_learning": { "total": 2438.4584212, "count": 1, "self": 1.7530878519728503, "children": { "TrainerController._reset_env": { "total": 4.525491329000033, "count": 1, "self": 4.525491329000033 }, "TrainerController.advance": { "total": 2432.020281343027, "count": 63963, "self": 1.7752535971121688, "children": { "env_step": { "total": 1739.875731707869, "count": 63963, "self": 1612.287845370729, "children": { "SubprocessEnvManager._take_step": { "total": 126.54448699816203, "count": 63963, "self": 5.214587332099654, "children": { "TorchPolicy.evaluate": { "total": 121.32989966606237, "count": 62553, "self": 121.32989966606237 } } }, "workers": { "total": 1.0433993389779062, "count": 63963, "self": 0.0, "children": { "worker_root": { "total": 2432.1782054769455, "count": 63963, "is_parallel": true, "self": 950.5988141699254, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018218929999420652, "count": 1, "is_parallel": true, "self": 0.0005905849993723677, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012313080005696975, "count": 8, "is_parallel": true, "self": 0.0012313080005696975 } } }, "UnityEnvironment.step": { "total": 0.07802595000066503, "count": 1, "is_parallel": true, "self": 0.0005818450008518994, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005028060004406143, "count": 1, "is_parallel": true, "self": 0.0005028060004406143 }, "communicator.exchange": { "total": 0.07502761599971564, "count": 1, "is_parallel": true, "self": 0.07502761599971564 }, "steps_from_proto": { "total": 0.001913682999656885, "count": 1, "is_parallel": true, "self": 0.00034027099991362775, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015734119997432572, "count": 8, "is_parallel": true, "self": 0.0015734119997432572 } } } } } } }, "UnityEnvironment.step": { "total": 1481.5793913070202, "count": 63962, "is_parallel": true, "self": 36.44222396619534, "children": { "UnityEnvironment._generate_step_input": { "total": 23.962392915007513, "count": 63962, "is_parallel": true, "self": 23.962392915007513 }, "communicator.exchange": { "total": 1308.7341079130456, "count": 63962, "is_parallel": true, "self": 1308.7341079130456 }, "steps_from_proto": { "total": 112.44066651277171, "count": 63962, "is_parallel": true, "self": 22.58210850327123, "children": { "_process_rank_one_or_two_observation": { "total": 89.85855800950048, "count": 511696, "is_parallel": true, "self": 89.85855800950048 } } } } } } } } } } }, "trainer_advance": { "total": 690.3692960380458, "count": 63963, "self": 3.09787722515739, "children": { "process_trajectory": { "total": 116.6892435258851, "count": 63963, "self": 116.42510706688608, "children": { "RLTrainer._checkpoint": { "total": 0.26413645899901894, "count": 2, "self": 0.26413645899901894 } } }, "_update_policy": { "total": 570.5821752870033, "count": 453, "self": 368.6402027899967, "children": { "TorchPPOOptimizer.update": { "total": 201.94197249700665, "count": 22815, "self": 201.94197249700665 } } } } } } }, "trainer_threads": { "total": 1.5170007827691734e-06, "count": 1, "self": 1.5170007827691734e-06 }, "TrainerController._save_models": { "total": 0.1595591589994001, "count": 1, "self": 0.002012392998949508, "children": { "RLTrainer._checkpoint": { "total": 0.1575467660004506, "count": 1, "self": 0.1575467660004506 } } } } } } }