{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3883911371231079, "min": 0.36615389585494995, "max": 1.4780291318893433, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 11651.734375, "min": 10996.333984375, "max": 44837.4921875, "count": 33 }, "Pyramids.Step.mean": { "value": 989913.0, "min": 29884.0, "max": 989913.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989913.0, "min": 29884.0, "max": 989913.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5519861578941345, "min": -0.1041940227150917, "max": 0.5704463720321655, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 155.66009521484375, "min": -25.00656509399414, "max": 159.72499084472656, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.07270178198814392, "min": -0.032321929931640625, "max": 0.23536927998065948, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 20.501903533935547, "min": -8.177448272705078, "max": 56.723995208740234, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06838832457045403, "min": 0.06434957535185323, "max": 0.07248848765242355, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9574365439863565, "min": 0.5004082077436065, "max": 1.0695368247882775, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.019082677292837098, "min": 0.000245954190323569, "max": 0.019082677292837098, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.26715748209971935, "min": 0.0031974044742063973, "max": 0.26715748209971935, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.690254579471428e-06, "min": 7.690254579471428e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001076635641126, "min": 0.0001076635641126, "max": 0.0035083298305567997, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10256338571428571, "min": 0.10256338571428571, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4358874, "min": 1.3886848, "max": 2.5694432000000007, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002660822328571429, "min": 0.0002660822328571429, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0037251512600000006, "min": 0.0037251512600000006, "max": 0.11696737568, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.008223719894886017, "min": 0.007561457809060812, "max": 0.45755529403686523, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.11513207852840424, "min": 0.10586041212081909, "max": 3.2028870582580566, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 329.03125, "min": 329.03125, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31587.0, "min": 16811.0, "max": 33889.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5667812330648303, "min": -0.9999742455059483, "max": 1.5778185848233313, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 150.4109983742237, "min": -31.99640166759491, "max": 150.4109983742237, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5667812330648303, "min": -0.9999742455059483, "max": 1.5778185848233313, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 150.4109983742237, "min": -31.99640166759491, "max": 150.4109983742237, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.027861727269131126, "min": 0.027861727269131126, "max": 8.881602389847531, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.6747258178365882, "min": 2.3100949179934105, "max": 150.98724062740803, "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": "1704897275", "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": "1704899519" }, "total": 2243.711638557, "count": 1, "self": 0.5279769449998639, "children": { "run_training.setup": { "total": 0.04670544100008556, "count": 1, "self": 0.04670544100008556 }, "TrainerController.start_learning": { "total": 2243.136956171, "count": 1, "self": 1.3858472920546774, "children": { "TrainerController._reset_env": { "total": 1.9694439810000404, "count": 1, "self": 1.9694439810000404 }, "TrainerController.advance": { "total": 2239.687541533945, "count": 63897, "self": 1.5774511009663001, "children": { "env_step": { "total": 1598.588285298983, "count": 63897, "self": 1462.736640909903, "children": { "SubprocessEnvManager._take_step": { "total": 134.96677188208764, "count": 63897, "self": 4.97253101509159, "children": { "TorchPolicy.evaluate": { "total": 129.99424086699605, "count": 62574, "self": 129.99424086699605 } } }, "workers": { "total": 0.8848725069924512, "count": 63897, "self": 0.0, "children": { "worker_root": { "total": 2237.8397658730114, "count": 63897, "is_parallel": true, "self": 900.9485674569771, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0016212680000080582, "count": 1, "is_parallel": true, "self": 0.0005039899995153974, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011172780004926608, "count": 8, "is_parallel": true, "self": 0.0011172780004926608 } } }, "UnityEnvironment.step": { "total": 0.06715852599995742, "count": 1, "is_parallel": true, "self": 0.0005948390000867221, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005317779998676997, "count": 1, "is_parallel": true, "self": 0.0005317779998676997 }, "communicator.exchange": { "total": 0.06428463200018086, "count": 1, "is_parallel": true, "self": 0.06428463200018086 }, "steps_from_proto": { "total": 0.0017472769998221338, "count": 1, "is_parallel": true, "self": 0.0003695040002185124, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013777729996036214, "count": 8, "is_parallel": true, "self": 0.0013777729996036214 } } } } } } }, "UnityEnvironment.step": { "total": 1336.8911984160343, "count": 63896, "is_parallel": true, "self": 36.01691302502854, "children": { "UnityEnvironment._generate_step_input": { "total": 25.79622405402756, "count": 63896, "is_parallel": true, "self": 25.79622405402756 }, "communicator.exchange": { "total": 1170.6501485889846, "count": 63896, "is_parallel": true, "self": 1170.6501485889846 }, "steps_from_proto": { "total": 104.42791274799356, "count": 63896, "is_parallel": true, "self": 21.45127447794721, "children": { "_process_rank_one_or_two_observation": { "total": 82.97663827004635, "count": 511168, "is_parallel": true, "self": 82.97663827004635 } } } } } } } } } } }, "trainer_advance": { "total": 639.5218051339959, "count": 63897, "self": 2.781705289018646, "children": { "process_trajectory": { "total": 132.25840883397177, "count": 63897, "self": 132.0645992829718, "children": { "RLTrainer._checkpoint": { "total": 0.19380955099995845, "count": 2, "self": 0.19380955099995845 } } }, "_update_policy": { "total": 504.4816910110055, "count": 453, "self": 301.07477906700046, "children": { "TorchPPOOptimizer.update": { "total": 203.40691194400506, "count": 22815, "self": 203.40691194400506 } } } } } } }, "trainer_threads": { "total": 1.1239999366807751e-06, "count": 1, "self": 1.1239999366807751e-06 }, "TrainerController._save_models": { "total": 0.09412224000016067, "count": 1, "self": 0.0014190400002007664, "children": { "RLTrainer._checkpoint": { "total": 0.0927031999999599, "count": 1, "self": 0.0927031999999599 } } } } } } }