{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.57216876745224, "min": 0.5012473464012146, "max": 1.4860557317733765, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 17311.5390625, "min": 14960.759765625, "max": 45080.98828125, "count": 33 }, "Pyramids.Step.mean": { "value": 989983.0, "min": 29952.0, "max": 989983.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989983.0, "min": 29952.0, "max": 989983.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.3864454925060272, "min": -0.11530105769634247, "max": 0.3864454925060272, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 102.79450225830078, "min": -27.787555694580078, "max": 102.79450225830078, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.1861555129289627, "min": -0.07764871418476105, "max": 0.5975057482719421, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 49.517364501953125, "min": -20.5769100189209, "max": 141.60885620117188, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07120051741819931, "min": 0.06416787754457733, "max": 0.07300743895455841, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0680077612729897, "min": 0.4985713914877083, "max": 1.0847092580105013, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.024501763297464802, "min": 0.000148369923246836, "max": 0.02993245838125256, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.36752644946197205, "min": 0.002077178925455704, "max": 0.36752644946197205, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.564997478366666e-06, "min": 7.564997478366666e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011347496217549999, "min": 0.00011347496217549999, "max": 0.0035070830309724002, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10252163333333335, "min": 0.10252163333333335, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5378245000000001, "min": 1.3886848, "max": 2.5690276, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026191117, "min": 0.00026191117, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.00392866755, "min": 0.00392866755, "max": 0.11692585724000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.011849983595311642, "min": 0.010776596143841743, "max": 0.6469508409500122, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.17774975299835205, "min": 0.1508723497390747, "max": 4.528656005859375, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 497.5151515151515, "min": 478.91803278688525, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 32836.0, "min": 15984.0, "max": 33248.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.3206060386516831, "min": -1.0000000521540642, "max": 1.3206060386516831, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 87.15999855101109, "min": -31.997201651334763, "max": 87.15999855101109, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.3206060386516831, "min": -1.0000000521540642, "max": 1.3206060386516831, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 87.15999855101109, "min": -31.997201651334763, "max": 87.15999855101109, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.06089903593811235, "min": 0.05631876753578268, "max": 14.76746123842895, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.019336371915415, "min": 3.3860047687776387, "max": 236.2793798148632, "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": "1705424463", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.2+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1705426578" }, "total": 2115.3410699990004, "count": 1, "self": 0.4884479200009082, "children": { "run_training.setup": { "total": 0.045695478999732586, "count": 1, "self": 0.045695478999732586 }, "TrainerController.start_learning": { "total": 2114.8069265999998, "count": 1, "self": 1.3800671641147346, "children": { "TrainerController._reset_env": { "total": 1.9801769910000075, "count": 1, "self": 1.9801769910000075 }, "TrainerController.advance": { "total": 2111.3555348888844, "count": 63400, "self": 1.4613187660233962, "children": { "env_step": { "total": 1501.6555938989327, "count": 63400, "self": 1368.0186057377377, "children": { "SubprocessEnvManager._take_step": { "total": 132.76172651810975, "count": 63400, "self": 4.714765706995422, "children": { "TorchPolicy.evaluate": { "total": 128.04696081111433, "count": 62569, "self": 128.04696081111433 } } }, "workers": { "total": 0.8752616430851958, "count": 63400, "self": 0.0, "children": { "worker_root": { "total": 2110.034735748097, "count": 63400, "is_parallel": true, "self": 861.3922840681062, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001799950000076933, "count": 1, "is_parallel": true, "self": 0.0005555239999921469, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012444260000847862, "count": 8, "is_parallel": true, "self": 0.0012444260000847862 } } }, "UnityEnvironment.step": { "total": 0.07825220999984595, "count": 1, "is_parallel": true, "self": 0.0006038179999450222, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005456990002130624, "count": 1, "is_parallel": true, "self": 0.0005456990002130624 }, "communicator.exchange": { "total": 0.07329587499998524, "count": 1, "is_parallel": true, "self": 0.07329587499998524 }, "steps_from_proto": { "total": 0.0038068179997026164, "count": 1, "is_parallel": true, "self": 0.0003842799997073598, "children": { "_process_rank_one_or_two_observation": { "total": 0.0034225379999952565, "count": 8, "is_parallel": true, "self": 0.0034225379999952565 } } } } } } }, "UnityEnvironment.step": { "total": 1248.6424516799907, "count": 63399, "is_parallel": true, "self": 35.478307690760175, "children": { "UnityEnvironment._generate_step_input": { "total": 26.328939685018213, "count": 63399, "is_parallel": true, "self": 26.328939685018213 }, "communicator.exchange": { "total": 1082.5896990381302, "count": 63399, "is_parallel": true, "self": 1082.5896990381302 }, "steps_from_proto": { "total": 104.24550526608209, "count": 63399, "is_parallel": true, "self": 21.10912433112071, "children": { "_process_rank_one_or_two_observation": { "total": 83.13638093496138, "count": 507192, "is_parallel": true, "self": 83.13638093496138 } } } } } } } } } } }, "trainer_advance": { "total": 608.2386222239284, "count": 63400, "self": 2.6630785149150142, "children": { "process_trajectory": { "total": 123.07945292002432, "count": 63400, "self": 122.88875141302333, "children": { "RLTrainer._checkpoint": { "total": 0.19070150700099475, "count": 2, "self": 0.19070150700099475 } } }, "_update_policy": { "total": 482.496090788989, "count": 449, "self": 286.1676695100223, "children": { "TorchPPOOptimizer.update": { "total": 196.32842127896674, "count": 22839, "self": 196.32842127896674 } } } } } } }, "trainer_threads": { "total": 9.229997885995544e-07, "count": 1, "self": 9.229997885995544e-07 }, "TrainerController._save_models": { "total": 0.09114663300078973, "count": 1, "self": 0.0016914420002649422, "children": { "RLTrainer._checkpoint": { "total": 0.08945519100052479, "count": 1, "self": 0.08945519100052479 } } } } } } }