{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3020292818546295, "min": 0.30125200748443604, "max": 1.4849423170089722, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 9075.3759765625, "min": 9042.3798828125, "max": 45047.2109375, "count": 33 }, "Pyramids.Step.mean": { "value": 989897.0, "min": 29952.0, "max": 989897.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989897.0, "min": 29952.0, "max": 989897.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6725330352783203, "min": -0.13907623291015625, "max": 0.7278995513916016, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 192.34445190429688, "min": -33.65644836425781, "max": 210.36297607421875, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.010753563605248928, "min": -0.0007151158060878515, "max": 0.433732807636261, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.075519323348999, "min": -0.20452311635017395, "max": 102.794677734375, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06579657682414618, "min": 0.06500817533482665, "max": 0.07416306532345837, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9211520755380465, "min": 0.5191414572642086, "max": 1.031899529938956, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015968983531206443, "min": 0.0004374867095154916, "max": 0.018075849530370242, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2235657694368902, "min": 0.004812353804670408, "max": 0.25306189342518337, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.223969020614289e-06, "min": 7.223969020614289e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010113556628860005, "min": 0.00010113556628860005, "max": 0.0035074874308375996, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10240795714285718, "min": 0.10240795714285718, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4337114000000004, "min": 1.3886848, "max": 2.6175660000000005, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002505549185714287, "min": 0.0002505549185714287, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003507768860000002, "min": 0.003507768860000002, "max": 0.11693932376, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.012262492440640926, "min": 0.012262492440640926, "max": 0.47736796736717224, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.17167489230632782, "min": 0.17167489230632782, "max": 3.341575860977173, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 273.4056603773585, "min": 258.0925925925926, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28981.0, "min": 15984.0, "max": 32718.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7077169658018734, "min": -1.0000000521540642, "max": 1.7296754204128917, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 181.01799837499857, "min": -31.997201651334763, "max": 197.18299792706966, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7077169658018734, "min": -1.0000000521540642, "max": 1.7296754204128917, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 181.01799837499857, "min": -31.997201651334763, "max": 197.18299792706966, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03478686358666548, "min": 0.03478686358666548, "max": 10.225412273779511, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.687407540186541, "min": 3.687407540186541, "max": 163.60659638047218, "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": "1750406448", "python_version": "3.10.12 | packaged by conda-forge | (main, Jun 23 2023, 22:40:32) [GCC 12.3.0]", "command_line_arguments": "/root/miniconda3/envs/stable-base/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./trained-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+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1750408808" }, "total": 2311.9355525010033, "count": 1, "self": 0.9288067599700298, "children": { "run_training.setup": { "total": 0.11956359501346014, "count": 1, "self": 0.11956359501346014 }, "TrainerController.start_learning": { "total": 2310.8871821460198, "count": 1, "self": 1.355852116830647, "children": { "TrainerController._reset_env": { "total": 13.314895067014731, "count": 1, "self": 13.314895067014731 }, "TrainerController.advance": { "total": 2296.1226301881834, "count": 64285, "self": 1.2122055814543273, "children": { "env_step": { "total": 1415.4235106999695, "count": 64285, "self": 1107.7691028590198, "children": { "SubprocessEnvManager._take_step": { "total": 306.79488046793267, "count": 64285, "self": 4.274932955362601, "children": { "TorchPolicy.evaluate": { "total": 302.51994751257007, "count": 62545, "self": 302.51994751257007 } } }, "workers": { "total": 0.8595273730170447, "count": 64285, "self": 0.0, "children": { "worker_root": { "total": 2307.9945283712004, "count": 64285, "is_parallel": true, "self": 1286.3969969660393, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.015067000000271946, "count": 1, "is_parallel": true, "self": 0.013245048030512407, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018219519697595388, "count": 8, "is_parallel": true, "self": 0.0018219519697595388 } } }, "UnityEnvironment.step": { "total": 0.0376017980161123, "count": 1, "is_parallel": true, "self": 0.00018978302250616252, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0001850039989221841, "count": 1, "is_parallel": true, "self": 0.0001850039989221841 }, "communicator.exchange": { "total": 0.03657073699287139, "count": 1, "is_parallel": true, "self": 0.03657073699287139 }, "steps_from_proto": { "total": 0.0006562740018125623, "count": 1, "is_parallel": true, "self": 0.00017474897322244942, "children": { "_process_rank_one_or_two_observation": { "total": 0.0004815250285901129, "count": 8, "is_parallel": true, "self": 0.0004815250285901129 } } } } } } }, "UnityEnvironment.step": { "total": 1021.5975314051611, "count": 64284, "is_parallel": true, "self": 14.317415886500385, "children": { "UnityEnvironment._generate_step_input": { "total": 10.98702951768064, "count": 64284, "is_parallel": true, "self": 10.98702951768064 }, "communicator.exchange": { "total": 954.0358871989592, "count": 64284, "is_parallel": true, "self": 954.0358871989592 }, "steps_from_proto": { "total": 42.257198802020866, "count": 64284, "is_parallel": true, "self": 11.2027663422341, "children": { "_process_rank_one_or_two_observation": { "total": 31.054432459786767, "count": 514272, "is_parallel": true, "self": 31.054432459786767 } } } } } } } } } } }, "trainer_advance": { "total": 879.4869139067596, "count": 64285, "self": 2.637953189580003, "children": { "process_trajectory": { "total": 152.32504985199193, "count": 64285, "self": 151.73665271201753, "children": { "RLTrainer._checkpoint": { "total": 0.5883971399744041, "count": 2, "self": 0.5883971399744041 } } }, "_update_policy": { "total": 724.5239108651876, "count": 450, "self": 308.7191272043565, "children": { "TorchPPOOptimizer.update": { "total": 415.80478366083116, "count": 22779, "self": 415.80478366083116 } } } } } } }, "trainer_threads": { "total": 5.860056262463331e-07, "count": 1, "self": 5.860056262463331e-07 }, "TrainerController._save_models": { "total": 0.09380418798536994, "count": 1, "self": 0.0013707990001421422, "children": { "RLTrainer._checkpoint": { "total": 0.0924333889852278, "count": 1, "self": 0.0924333889852278 } } } } } } }