{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3509610891342163, "min": 0.3087957203388214, "max": 0.36777380108833313, "count": 14 }, "Pyramids.Policy.Entropy.sum": { "value": 10590.6015625, "min": 3339.9345703125, "max": 11009.6767578125, "count": 14 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 261.5739130434783, "min": 208.8709677419355, "max": 333.15555555555557, "count": 14 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30081.0, "min": 6475.0, "max": 30810.0, "count": 14 }, "Pyramids.Step.mean": { "value": 1799967.0, "min": 1409913.0, "max": 1799967.0, "count": 14 }, "Pyramids.Step.sum": { "value": 1799967.0, "min": 1409913.0, "max": 1799967.0, "count": 14 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6859020590782166, "min": 0.578832745552063, "max": 0.6859020590782166, "count": 14 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 200.2834014892578, "min": 53.8724479675293, "max": 200.2834014892578, "count": 14 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 21.957359313964844, "min": 2.9718246459960938, "max": 21.957359313964844, "count": 14 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 6411.548828125, "min": 264.4924011230469, "max": 6411.548828125, "count": 14 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.720510334675682, "min": 1.629107512453551, "max": 1.7911290161071285, "count": 14 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 199.5791988223791, "min": 55.524999499320984, "max": 199.5791988223791, "count": 14 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.720510334675682, "min": 1.629107512453551, "max": 1.7911290161071285, "count": 14 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 199.5791988223791, "min": 55.524999499320984, "max": 199.5791988223791, "count": 14 }, "Pyramids.Policy.RndReward.mean": { "value": 0.22894134176172445, "min": 0.22894134176172445, "max": 0.3622605609319483, "count": 14 }, "Pyramids.Policy.RndReward.sum": { "value": 26.557195644360036, "min": 7.3203921407694, "max": 32.60345048387535, "count": 14 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07270944114134181, "min": 0.06266858351548708, "max": 0.07270944114134181, "count": 14 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0179321759787854, "min": 0.27831401882576756, "max": 1.0420461169269402, "count": 14 }, "Pyramids.Losses.ValueLoss.mean": { "value": 21.68147027705397, "min": 0.471697402519307, "max": 21.68147027705397, "count": 14 }, "Pyramids.Losses.ValueLoss.sum": { "value": 303.54058387875557, "min": 1.9932998442091048, "max": 303.54058387875557, "count": 14 }, "Pyramids.Policy.LearningRate.mean": { "value": 2.424611096591275e-06, "min": 2.424611096591275e-06, "max": 6.578182807274999e-05, "count": 14 }, "Pyramids.Policy.LearningRate.sum": { "value": 3.394455535227785e-05, "min": 3.394455535227785e-05, "max": 0.0008766917744364446, "count": 14 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10080817063492063, "min": 0.10080817063492063, "max": 0.12192725000000001, "count": 14 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4113143888888888, "min": 0.48770900000000006, "max": 1.7875094444444446, "count": 14 }, "Pyramids.Policy.Beta.mean": { "value": 9.073624642857163e-05, "min": 9.073624642857163e-05, "max": 0.002200532275, "count": 14 }, "Pyramids.Policy.Beta.sum": { "value": 0.0012703074500000028, "min": 0.0012703074500000028, "max": 0.0293337992, "count": 14 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.027669908478856087, "min": 0.027669908478856087, "max": 0.03692689538002014, "count": 14 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.3873787224292755, "min": 0.14770758152008057, "max": 0.49223601818084717, "count": 14 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 14 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 14 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1728319279", "python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [GCC 11.4.0]", "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 --resume", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.4.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1728320196" }, "total": 916.5547743960005, "count": 1, "self": 1.1799581080003918, "children": { "run_training.setup": { "total": 0.06476543600001605, "count": 1, "self": 0.06476543600001605 }, "TrainerController.start_learning": { "total": 915.3100508520001, "count": 1, "self": 0.5411470719573117, "children": { "TrainerController._reset_env": { "total": 2.24071387100048, "count": 1, "self": 2.24071387100048 }, "TrainerController.advance": { "total": 912.4310510820433, "count": 26117, "self": 0.5757557350352727, "children": { "env_step": { "total": 710.9093044849951, "count": 26117, "self": 649.9562996429831, "children": { "SubprocessEnvManager._take_step": { "total": 60.62759578393161, "count": 26117, "self": 1.8369352299632737, "children": { "TorchPolicy.evaluate": { "total": 58.79066055396834, "count": 25071, "self": 58.79066055396834 } } }, "workers": { "total": 0.3254090580803677, "count": 26117, "self": 0.0, "children": { "worker_root": { "total": 913.3407672259527, "count": 26117, "is_parallel": true, "self": 311.62826983305786, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0031315679998442647, "count": 1, "is_parallel": true, "self": 0.0009635180003897403, "children": { "_process_rank_one_or_two_observation": { "total": 0.0021680499994545244, "count": 8, "is_parallel": true, "self": 0.0021680499994545244 } } }, "UnityEnvironment.step": { "total": 0.09401083200009452, "count": 1, "is_parallel": true, "self": 0.0006287340002018027, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005019809996156255, "count": 1, "is_parallel": true, "self": 0.0005019809996156255 }, "communicator.exchange": { "total": 0.09124633700048435, "count": 1, "is_parallel": true, "self": 0.09124633700048435 }, "steps_from_proto": { "total": 0.0016337799997927505, "count": 1, "is_parallel": true, "self": 0.0003371640004843357, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012966159993084148, "count": 8, "is_parallel": true, "self": 0.0012966159993084148 } } } } } } }, "UnityEnvironment.step": { "total": 601.7124973928949, "count": 26116, "is_parallel": true, "self": 13.173401732853563, "children": { "UnityEnvironment._generate_step_input": { "total": 9.298754634973193, "count": 26116, "is_parallel": true, "self": 9.298754634973193 }, "communicator.exchange": { "total": 539.8244959001067, "count": 26116, "is_parallel": true, "self": 539.8244959001067 }, "steps_from_proto": { "total": 39.41584512496138, "count": 26116, "is_parallel": true, "self": 8.129025020915833, "children": { "_process_rank_one_or_two_observation": { "total": 31.286820104045546, "count": 208928, "is_parallel": true, "self": 31.286820104045546 } } } } } } } } } } }, "trainer_advance": { "total": 200.94599086201288, "count": 26117, "self": 1.07309663295473, "children": { "process_trajectory": { "total": 54.34334475605556, "count": 26117, "self": 54.253657134056084, "children": { "RLTrainer._checkpoint": { "total": 0.08968762199947378, "count": 1, "self": 0.08968762199947378 } } }, "_update_policy": { "total": 145.5295494730026, "count": 189, "self": 81.035269021967, "children": { "TorchPPOOptimizer.update": { "total": 64.49428045103559, "count": 6066, "self": 64.49428045103559 } } } } } } }, "trainer_threads": { "total": 1.5699997675255872e-06, "count": 1, "self": 1.5699997675255872e-06 }, "TrainerController._save_models": { "total": 0.09713725699930364, "count": 1, "self": 0.0016087909989437321, "children": { "RLTrainer._checkpoint": { "total": 0.09552846600035991, "count": 1, "self": 0.09552846600035991 } } } } } } }