{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.27767232060432434, "min": 0.27767232060432434, "max": 1.4096121788024902, "count": 46 }, "Pyramids.Policy.Entropy.sum": { "value": 8192.4443359375, "min": 8192.4443359375, "max": 42761.99609375, "count": 46 }, "Pyramids.Step.mean": { "value": 1379917.0, "min": 29952.0, "max": 1379917.0, "count": 46 }, "Pyramids.Step.sum": { "value": 1379917.0, "min": 29952.0, "max": 1379917.0, "count": 46 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6702777147293091, "min": -0.10634979605674744, "max": 0.7332963347434998, "count": 46 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 192.3697052001953, "min": -25.630300521850586, "max": 210.4560546875, "count": 46 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.011026584543287754, "min": -0.022578353062272072, "max": 0.41423195600509644, "count": 46 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.1646296977996826, "min": -6.502565860748291, "max": 98.1729736328125, "count": 46 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06490180985278161, "min": 0.06473938323098181, "max": 0.07377091803404366, "count": 46 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9086253379389425, "min": 0.5163964262383056, "max": 1.046531137919017, "count": 46 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016222578668943246, "min": 0.0005933448658925789, "max": 0.018473621550670248, "count": 46 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.22711610136520544, "min": 0.006526793524818368, "max": 0.25863070170938346, "count": 46 }, "Pyramids.Policy.LearningRate.mean": { "value": 0.00016357413833244523, "min": 0.00016357413833244523, "max": 0.00029838354339596195, "count": 46 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0022900379366542333, "min": 0.0020886848037717336, "max": 0.0038433409188863995, "count": 46 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.15452469761904766, "min": 0.15452469761904766, "max": 0.19946118095238097, "count": 46 }, "Pyramids.Policy.Epsilon.sum": { "value": 2.163345766666667, "min": 1.3962282666666668, "max": 2.7074752333333336, "count": 46 }, "Pyramids.Policy.Beta.mean": { "value": 0.005457017292142856, "min": 0.005457017292142856, "max": 0.009946171977142856, "count": 46 }, "Pyramids.Policy.Beta.sum": { "value": 0.07639824208999998, "min": 0.06962320384, "max": 0.12812324864, "count": 46 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009080156683921814, "min": 0.00870793592184782, "max": 0.5393413305282593, "count": 46 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1271221935749054, "min": 0.12355020642280579, "max": 3.7753891944885254, "count": 46 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 270.8818181818182, "min": 260.35849056603774, "max": 999.0, "count": 46 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29797.0, "min": 15984.0, "max": 34313.0, "count": 46 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.728747730051075, "min": -1.0000000521540642, "max": 1.7344700745028307, "count": 46 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 191.89099803566933, "min": -30.9994016289711, "max": 202.9329987168312, "count": 46 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.728747730051075, "min": -1.0000000521540642, "max": 1.7344700745028307, "count": 46 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 191.89099803566933, "min": -30.9994016289711, "max": 202.9329987168312, "count": 46 }, "Pyramids.Policy.RndReward.mean": { "value": 0.025869574275356508, "min": 0.02541784507653047, "max": 10.907942678779364, "count": 46 }, "Pyramids.Policy.RndReward.sum": { "value": 2.8715227445645723, "min": 2.7197094231887604, "max": 174.52708286046982, "count": 46 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 46 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 46 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1785083708", "python_version": "3.10.6 (main, Oct 24 2022, 16:07:47) [GCC 11.2.0]", "command_line_arguments": "/usr/local/miniconda/envs/mlagents_env/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1785088834" }, "total": 5126.115679116001, "count": 1, "self": 1.7790465020007105, "children": { "run_training.setup": { "total": 0.027551514000151656, "count": 1, "self": 0.027551514000151656 }, "TrainerController.start_learning": { "total": 5124.3090811, "count": 1, "self": 3.039634068961277, "children": { "TrainerController._reset_env": { "total": 3.3859890359999554, "count": 1, "self": 3.3859890359999554 }, "TrainerController.advance": { "total": 5117.878001582038, "count": 88805, "self": 3.278368179823701, "children": { "env_step": { "total": 3649.443852909974, "count": 88805, "self": 3425.412943611107, "children": { "SubprocessEnvManager._take_step": { "total": 222.02518528104065, "count": 88805, "self": 9.8006042320103, "children": { "TorchPolicy.evaluate": { "total": 212.22458104903035, "count": 86561, "self": 212.22458104903035 } } }, "workers": { "total": 2.0057240178261964, "count": 88804, "self": 0.0, "children": { "worker_root": { "total": 5113.31390888507, "count": 88804, "is_parallel": true, "self": 1947.507215571205, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005487924000135536, "count": 1, "is_parallel": true, "self": 0.0038483509997604415, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016395730003750941, "count": 8, "is_parallel": true, "self": 0.0016395730003750941 } } }, "UnityEnvironment.step": { "total": 0.06897178000008353, "count": 1, "is_parallel": true, "self": 0.0007104239998625417, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005250980002529104, "count": 1, "is_parallel": true, "self": 0.0005250980002529104 }, "communicator.exchange": { "total": 0.06580355300002338, "count": 1, "is_parallel": true, "self": 0.06580355300002338 }, "steps_from_proto": { "total": 0.00193270499994469, "count": 1, "is_parallel": true, "self": 0.00044072999980926397, "children": { "_process_rank_one_or_two_observation": { "total": 0.001491975000135426, "count": 8, "is_parallel": true, "self": 0.001491975000135426 } } } } } } }, "UnityEnvironment.step": { "total": 3165.8066933138653, "count": 88803, "is_parallel": true, "self": 68.36412122989941, "children": { "UnityEnvironment._generate_step_input": { "total": 43.62124804599216, "count": 88803, "is_parallel": true, "self": 43.62124804599216 }, "communicator.exchange": { "total": 2853.7185298640093, "count": 88803, "is_parallel": true, "self": 2853.7185298640093 }, "steps_from_proto": { "total": 200.1027941739644, "count": 88803, "is_parallel": true, "self": 39.4414992925299, "children": { "_process_rank_one_or_two_observation": { "total": 160.66129488143451, "count": 710424, "is_parallel": true, "self": 160.66129488143451 } } } } } } } } } } }, "trainer_advance": { "total": 1465.1557804922409, "count": 88804, "self": 6.032427481146897, "children": { "process_trajectory": { "total": 207.44420364109283, "count": 88804, "self": 206.82601886009252, "children": { "RLTrainer._checkpoint": { "total": 0.6181847810003092, "count": 2, "self": 0.6181847810003092 } } }, "_update_policy": { "total": 1251.6791493700011, "count": 625, "self": 474.78344783402554, "children": { "TorchPPOOptimizer.update": { "total": 776.8957015359756, "count": 31524, "self": 776.8957015359756 } } } } } } }, "trainer_threads": { "total": 1.7660004232311621e-06, "count": 1, "self": 1.7660004232311621e-06 }, "TrainerController._save_models": { "total": 0.005454647000078694, "count": 1, "self": 4.52900003438117e-05, "children": { "RLTrainer._checkpoint": { "total": 0.005409356999734882, "count": 1, "self": 0.005409356999734882 } } } } } } }