{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4158688485622406, "min": 0.4158688485622406, "max": 1.4334027767181396, "count": 38 }, "Pyramids.Policy.Entropy.sum": { "value": 12482.7197265625, "min": 12482.7197265625, "max": 43483.70703125, "count": 38 }, "Pyramids.Step.mean": { "value": 1139954.0, "min": 29902.0, "max": 1139954.0, "count": 38 }, "Pyramids.Step.sum": { "value": 1139954.0, "min": 29902.0, "max": 1139954.0, "count": 38 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.4747034013271332, "min": -0.09710239619016647, "max": 0.5281603932380676, "count": 38 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 129.11932373046875, "min": -23.40167808532715, "max": 143.1314697265625, "count": 38 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.003889927174896002, "min": -0.0016563987592235208, "max": 0.32075613737106323, "count": 38 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 1.0580601692199707, "min": -0.4207252860069275, "max": 76.01920318603516, "count": 38 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0710136718435457, "min": 0.06403720775751708, "max": 0.0738912057907631, "count": 38 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9941914058096398, "min": 0.5896578854585877, "max": 1.1083680868614465, "count": 38 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015340565439102996, "min": 0.00017771699159691522, "max": 0.016487775863264505, "count": 38 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21476791614744195, "min": 0.002310320890759898, "max": 0.21476791614744195, "count": 38 }, "Pyramids.Policy.LearningRate.mean": { "value": 0.00018746620893984764, "min": 0.00018746620893984764, "max": 0.0002984035255321583, "count": 38 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.002624526925157867, "min": 0.0023872282042572664, "max": 0.0039274579908473665, "count": 38 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1624887238095238, "min": 0.1624887238095238, "max": 0.19946784166666667, "count": 38 }, "Pyramids.Policy.Epsilon.sum": { "value": 2.2748421333333333, "min": 1.5957427333333334, "max": 2.709152633333334, "count": 38 }, "Pyramids.Policy.Beta.mean": { "value": 0.0062526235085714294, "min": 0.0062526235085714294, "max": 0.0099468373825, "count": 38 }, "Pyramids.Policy.Beta.sum": { "value": 0.08753672912000002, "min": 0.07957469906, "max": 0.13092434807000003, "count": 38 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.007184040267020464, "min": 0.006830547470599413, "max": 0.5138049721717834, "count": 38 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.10057656466960907, "min": 0.09562766551971436, "max": 4.110439777374268, "count": 38 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 377.5243902439024, "min": 377.15384615384613, "max": 999.0, "count": 38 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30957.0, "min": 16829.0, "max": 33338.0, "count": 38 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5004975409587709, "min": -0.9998645681527353, "max": 1.5202461353097207, "count": 38 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 123.04079835861921, "min": -30.995801612734795, "max": 123.04079835861921, "count": 38 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5004975409587709, "min": -0.9998645681527353, "max": 1.5202461353097207, "count": 38 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 123.04079835861921, "min": -30.995801612734795, "max": 123.04079835861921, "count": 38 }, "Pyramids.Policy.RndReward.mean": { "value": 0.028667418900934025, "min": 0.028667418900934025, "max": 11.179093125988455, "count": 38 }, "Pyramids.Policy.RndReward.sum": { "value": 2.35072834987659, "min": 2.060942495649215, "max": 190.04458314180374, "count": 38 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 38 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 38 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1749370516", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "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": "1.2.0.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": "1749373063" }, "total": 2547.045255888, "count": 1, "self": 0.5769756640006563, "children": { "run_training.setup": { "total": 0.02166395300014301, "count": 1, "self": 0.02166395300014301 }, "TrainerController.start_learning": { "total": 2546.4466162709996, "count": 1, "self": 1.5921405469612182, "children": { "TrainerController._reset_env": { "total": 2.2480135420000806, "count": 1, "self": 2.2480135420000806 }, "TrainerController.advance": { "total": 2542.3611137560397, "count": 73564, "self": 1.658556076019977, "children": { "env_step": { "total": 1745.9980852639992, "count": 73564, "self": 1558.3319822050498, "children": { "SubprocessEnvManager._take_step": { "total": 186.72180298093986, "count": 73564, "self": 5.507459227936806, "children": { "TorchPolicy.evaluate": { "total": 181.21434375300305, "count": 72429, "self": 181.21434375300305 } } }, "workers": { "total": 0.944300078009519, "count": 73564, "self": 0.0, "children": { "worker_root": { "total": 2539.0924085559723, "count": 73564, "is_parallel": true, "self": 1115.5424509109469, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0032895009999265312, "count": 1, "is_parallel": true, "self": 0.0009728090003591205, "children": { "_process_rank_one_or_two_observation": { "total": 0.0023166919995674107, "count": 8, "is_parallel": true, "self": 0.0023166919995674107 } } }, "UnityEnvironment.step": { "total": 0.0506185239999013, "count": 1, "is_parallel": true, "self": 0.0005873399998108653, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004933090001486562, "count": 1, "is_parallel": true, "self": 0.0004933090001486562 }, "communicator.exchange": { "total": 0.0478301680000186, "count": 1, "is_parallel": true, "self": 0.0478301680000186 }, "steps_from_proto": { "total": 0.0017077069999231753, "count": 1, "is_parallel": true, "self": 0.00034873799972956476, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013589690001936106, "count": 8, "is_parallel": true, "self": 0.0013589690001936106 } } } } } } }, "UnityEnvironment.step": { "total": 1423.5499576450254, "count": 73563, "is_parallel": true, "self": 37.52510681484796, "children": { "UnityEnvironment._generate_step_input": { "total": 28.12623081507263, "count": 73563, "is_parallel": true, "self": 28.12623081507263 }, "communicator.exchange": { "total": 1242.7567264091165, "count": 73563, "is_parallel": true, "self": 1242.7567264091165 }, "steps_from_proto": { "total": 115.14189360598834, "count": 73563, "is_parallel": true, "self": 23.262269771694264, "children": { "_process_rank_one_or_two_observation": { "total": 91.87962383429408, "count": 588504, "is_parallel": true, "self": 91.87962383429408 } } } } } } } } } } }, "trainer_advance": { "total": 794.7044724160207, "count": 73564, "self": 2.988573217009389, "children": { "process_trajectory": { "total": 153.60908939901242, "count": 73564, "self": 153.39238200101204, "children": { "RLTrainer._checkpoint": { "total": 0.21670739800038064, "count": 2, "self": 0.21670739800038064 } } }, "_update_policy": { "total": 638.1068097999989, "count": 530, "self": 351.4865674349787, "children": { "TorchPPOOptimizer.update": { "total": 286.6202423650202, "count": 26347, "self": 286.6202423650202 } } } } } } }, "trainer_threads": { "total": 1.312999302172102e-06, "count": 1, "self": 1.312999302172102e-06 }, "TrainerController._save_models": { "total": 0.24534711299929768, "count": 1, "self": 0.008250718999079254, "children": { "RLTrainer._checkpoint": { "total": 0.23709639400021842, "count": 1, "self": 0.23709639400021842 } } } } } } }