{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.1557580977678299, "min": 0.14232201874256134, "max": 1.4221614599227905, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 4707.6328125, "min": 4262.8291015625, "max": 43142.69140625, "count": 100 }, "Pyramids.Step.mean": { "value": 2999952.0, "min": 29908.0, "max": 2999952.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999952.0, "min": 29908.0, "max": 2999952.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.8571072816848755, "min": -0.085138700902462, "max": 0.9104765057563782, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 267.41748046875, "min": -20.43328857421875, "max": 280.4267578125, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.030598163604736328, "min": -0.004368090070784092, "max": 0.3133503794670105, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 9.546627044677734, "min": -1.1225991249084473, "max": 74.2640380859375, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07082819727510155, "min": 0.06300574126812444, "max": 0.0770406294735818, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9915947618514217, "min": 0.4968911905380919, "max": 1.155609442103727, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016107676150547912, "min": 0.0007578454199346445, "max": 0.01744761026167821, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.22550746610767075, "min": 0.009851990459150379, "max": 0.2513933608909914, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.4262280960523795e-06, "min": 1.4262280960523795e-06, "max": 0.00029838354339596195, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 1.9967193344733314e-05, "min": 1.9967193344733314e-05, "max": 0.003892396002534733, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1004753761904762, "min": 0.1004753761904762, "max": 0.19946118095238097, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4066552666666667, "min": 1.3962282666666668, "max": 2.797465266666667, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 5.749008142857138e-05, "min": 5.749008142857138e-05, "max": 0.009946171977142856, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.0008048611399999993, "min": 0.0008048611399999993, "max": 0.12976678013999998, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.00681902002543211, "min": 0.006652852054685354, "max": 0.49473491311073303, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.09546627849340439, "min": 0.09471222758293152, "max": 3.463144302368164, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 198.95333333333335, "min": 198.93835616438355, "max": 990.8709677419355, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29843.0, "min": 16835.0, "max": 33696.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.8010466601451238, "min": -0.9272129538078462, "max": 1.8010466601451238, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 270.15699902176857, "min": -28.743601568043232, "max": 270.15699902176857, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.8010466601451238, "min": -0.9272129538078462, "max": 1.8010466601451238, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 270.15699902176857, "min": -28.743601568043232, "max": 270.15699902176857, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.01411828581234052, "min": 0.01411828581234052, "max": 9.088839991127744, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 2.1177428718510782, "min": 2.0807449555795756, "max": 154.51027984917164, "count": 100 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1680625123", "python_version": "3.10.10 | packaged by conda-forge | (main, Mar 24 2023, 20:08:06) [GCC 11.3.0]", "command_line_arguments": "/home/kian/anaconda3/envs/torch-2/bin/mlagents-learn ./ml-agents/config/ppo/PyramidsRND.yaml --env=./ml-agents/training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training2 --no-graphics", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.0.0", "numpy_version": "1.21.2", "end_time_seconds": "1680633468" }, "total": 8344.656527563999, "count": 1, "self": 0.6487447669969697, "children": { "run_training.setup": { "total": 0.013877202000003308, "count": 1, "self": 0.013877202000003308 }, "TrainerController.start_learning": { "total": 8343.993905595002, "count": 1, "self": 3.2417968647805537, "children": { "TrainerController._reset_env": { "total": 3.878523504000441, "count": 1, "self": 3.878523504000441 }, "TrainerController.advance": { "total": 8336.832473621222, "count": 195738, "self": 2.7819726879552036, "children": { "env_step": { "total": 3881.525260359399, "count": 195738, "self": 1862.4469721596079, "children": { "SubprocessEnvManager._take_step": { "total": 2017.264238799039, "count": 195738, "self": 8.877353178607336, "children": { "TorchPolicy.evaluate": { "total": 2008.3868856204317, "count": 187574, "self": 2008.3868856204317 } } }, "workers": { "total": 1.8140494007520829, "count": 195738, "self": 0.0, "children": { "worker_root": { "total": 8340.138424857758, "count": 195738, "is_parallel": true, "self": 6662.171141660773, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001051617000484839, "count": 1, "is_parallel": true, "self": 0.0003240490013922681, "children": { "_process_rank_one_or_two_observation": { "total": 0.000727567999092571, "count": 8, "is_parallel": true, "self": 0.000727567999092571 } } }, "UnityEnvironment.step": { "total": 0.018285617000401544, "count": 1, "is_parallel": true, "self": 0.00019925000106013613, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00021848899996257387, "count": 1, "is_parallel": true, "self": 0.00021848899996257387 }, "communicator.exchange": { "total": 0.01718230099959328, "count": 1, "is_parallel": true, "self": 0.01718230099959328 }, "steps_from_proto": { "total": 0.0006855769997855532, "count": 1, "is_parallel": true, "self": 0.0001556389997858787, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005299379999996745, "count": 8, "is_parallel": true, "self": 0.0005299379999996745 } } } } } } }, "UnityEnvironment.step": { "total": 1677.9672831969847, "count": 195737, "is_parallel": true, "self": 40.33503694632418, "children": { "UnityEnvironment._generate_step_input": { "total": 30.266844403903633, "count": 195737, "is_parallel": true, "self": 30.266844403903633 }, "communicator.exchange": { "total": 1480.0816756993845, "count": 195737, "is_parallel": true, "self": 1480.0816756993845 }, "steps_from_proto": { "total": 127.28372614737236, "count": 195737, "is_parallel": true, "self": 27.574009737836604, "children": { "_process_rank_one_or_two_observation": { "total": 99.70971640953576, "count": 1565896, "is_parallel": true, "self": 99.70971640953576 } } } } } } } } } } }, "trainer_advance": { "total": 4452.5252405738665, "count": 195738, "self": 6.786533768141453, "children": { "process_trajectory": { "total": 1066.4394581657407, "count": 195738, "self": 1064.5123476307408, "children": { "RLTrainer._checkpoint": { "total": 1.9271105349998834, "count": 6, "self": 1.9271105349998834 } } }, "_update_policy": { "total": 3379.2992486399844, "count": 1403, "self": 1645.2452537600257, "children": { "TorchPPOOptimizer.update": { "total": 1734.0539948799587, "count": 68409, "self": 1734.0539948799587 } } } } } } }, "trainer_threads": { "total": 5.299989425111562e-07, "count": 1, "self": 5.299989425111562e-07 }, "TrainerController._save_models": { "total": 0.04111107500102662, "count": 1, "self": 0.0013105560010444606, "children": { "RLTrainer._checkpoint": { "total": 0.03980051899998216, "count": 1, "self": 0.03980051899998216 } } } } } } }