{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4627936780452728, "min": 0.4609237313270569, "max": 1.4670432806015015, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 13965.26171875, "min": 13694.9658203125, "max": 44504.2265625, "count": 33 }, "Pyramids.Step.mean": { "value": 989951.0, "min": 29952.0, "max": 989951.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989951.0, "min": 29952.0, "max": 989951.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.47099894285202026, "min": -0.10116783529520035, "max": 0.5975823998451233, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 126.69871520996094, "min": -24.38144874572754, "max": 166.72549438476562, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.032067522406578064, "min": -0.009064771234989166, "max": 0.3494204878807068, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 8.626163482666016, "min": -2.5834598541259766, "max": 83.86091613769531, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06879097547928159, "min": 0.06395186080159428, "max": 0.07368961878207966, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9630736567099423, "min": 0.4905884915637655, "max": 1.046715185220819, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.013607813684627346, "min": 0.00010716248847572122, "max": 0.016594731883428877, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.19050939158478283, "min": 0.001500274838660097, "max": 0.22457158137209868, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.3316261275857155e-06, "min": 7.3316261275857155e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010264276578620002, "min": 0.00010264276578620002, "max": 0.0033822440725854, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10244384285714285, "min": 0.10244384285714285, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4342138, "min": 1.3691136000000002, "max": 2.5274146000000006, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002541399014285715, "min": 0.0002541399014285715, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003557958620000001, "min": 0.003557958620000001, "max": 0.11276871854000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.012034490704536438, "min": 0.011664292775094509, "max": 0.5429760217666626, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.16848286986351013, "min": 0.16330009698867798, "max": 3.8008322715759277, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 370.1578947368421, "min": 309.46067415730334, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28132.0, "min": 15984.0, "max": 32954.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5245552441399348, "min": -1.0000000521540642, "max": 1.6873888729347124, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 115.86619855463505, "min": -32.000001668930054, "max": 151.8649985641241, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5245552441399348, "min": -1.0000000521540642, "max": 1.6873888729347124, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 115.86619855463505, "min": -32.000001668930054, "max": 151.8649985641241, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.046563367092235956, "min": 0.03925282833774367, "max": 11.243016171269119, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.5388158990099328, "min": 3.5327545503969304, "max": 179.8882587403059, "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": "1781485881", "python_version": "3.10.12 (main, Mar 3 2026, 11:56:32) [GCC 11.4.0]", "command_line_arguments": "/mnt/d/space/hf-rl/bonus-unit1/.venv-wsl/bin/mlagents-learn /mnt/d/space/hf-rl/bonus-unit1/vendor/ml-agents/config/ppo/PyramidsRND.yaml --env=/mnt/d/space/hf-rl/unit5/envs/linux/Pyramids/Pyramids --run-id=Pyramids1 --no-graphics --num-envs=1 --timeout-wait=180 --force", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.7.1+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1781489831" }, "total": 3609.453242256, "count": 1, "self": 10.022552974999599, "children": { "run_training.setup": { "total": 0.26663304800000276, "count": 1, "self": 0.26663304800000276 }, "TrainerController.start_learning": { "total": 3599.1640562330003, "count": 1, "self": 1.4115560490313328, "children": { "TrainerController._reset_env": { "total": 30.301432078999994, "count": 1, "self": 30.301432078999994 }, "TrainerController.advance": { "total": 3567.051907325969, "count": 63713, "self": 1.4789411080660102, "children": { "env_step": { "total": 2275.047270172955, "count": 63713, "self": 1937.007651836906, "children": { "SubprocessEnvManager._take_step": { "total": 337.176277736035, "count": 63713, "self": 5.020477708085764, "children": { "TorchPolicy.evaluate": { "total": 332.1558000279492, "count": 62557, "self": 332.1558000279492 } } }, "workers": { "total": 0.8633406000139701, "count": 63713, "self": 0.0, "children": { "worker_root": { "total": 3592.9451779260157, "count": 63713, "is_parallel": true, "self": 1771.6236680289658, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.009187221999994222, "count": 1, "is_parallel": true, "self": 0.0034824009999852024, "children": { "_process_rank_one_or_two_observation": { "total": 0.005704821000009019, "count": 8, "is_parallel": true, "self": 0.005704821000009019 } } }, "UnityEnvironment.step": { "total": 0.07209176899999648, "count": 1, "is_parallel": true, "self": 0.0004161669999689366, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0006842040000094585, "count": 1, "is_parallel": true, "self": 0.0006842040000094585 }, "communicator.exchange": { "total": 0.06980034800000112, "count": 1, "is_parallel": true, "self": 0.06980034800000112 }, "steps_from_proto": { "total": 0.0011910500000169577, "count": 1, "is_parallel": true, "self": 0.0002942700000119203, "children": { "_process_rank_one_or_two_observation": { "total": 0.0008967800000050374, "count": 8, "is_parallel": true, "self": 0.0008967800000050374 } } } } } } }, "UnityEnvironment.step": { "total": 1821.32150989705, "count": 63712, "is_parallel": true, "self": 28.41476359915214, "children": { "UnityEnvironment._generate_step_input": { "total": 19.253633228977293, "count": 63712, "is_parallel": true, "self": 19.253633228977293 }, "communicator.exchange": { "total": 1685.6341891638988, "count": 63712, "is_parallel": true, "self": 1685.6341891638988 }, "steps_from_proto": { "total": 88.01892390502167, "count": 63712, "is_parallel": true, "self": 20.555391886965822, "children": { "_process_rank_one_or_two_observation": { "total": 67.46353201805584, "count": 509696, "is_parallel": true, "self": 67.46353201805584 } } } } } } } } } } }, "trainer_advance": { "total": 1290.5256960449478, "count": 63713, "self": 2.2441690699620267, "children": { "process_trajectory": { "total": 191.43753943798595, "count": 63713, "self": 189.23052914998584, "children": { "RLTrainer._checkpoint": { "total": 2.207010288000106, "count": 5, "self": 2.207010288000106 } } }, "_update_policy": { "total": 1096.8439875369997, "count": 447, "self": 409.2008528670044, "children": { "TorchPPOOptimizer.update": { "total": 687.6431346699953, "count": 22842, "self": 687.6431346699953 } } } } } } }, "trainer_threads": { "total": 8.000001798791345e-07, "count": 1, "self": 8.000001798791345e-07 }, "TrainerController._save_models": { "total": 0.3991599790001601, "count": 1, "self": 0.04514143900041745, "children": { "RLTrainer._checkpoint": { "total": 0.35401853999974264, "count": 1, "self": 0.35401853999974264 } } } } } } }