{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.413528174161911, "min": 0.4067316949367523, "max": 1.4837636947631836, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 12399.228515625, "min": 12358.1357421875, "max": 45011.45703125, "count": 33 }, "Pyramids.Step.mean": { "value": 989944.0, "min": 29952.0, "max": 989944.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989944.0, "min": 29952.0, "max": 989944.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.42325180768966675, "min": -0.09376850724220276, "max": 0.45588377118110657, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 113.00823211669922, "min": -22.598209381103516, "max": 123.54450225830078, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.05050178989768028, "min": -0.05050178989768028, "max": 0.28233885765075684, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -13.483978271484375, "min": -13.483978271484375, "max": 67.56222534179688, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06612139922938133, "min": 0.06500746173853758, "max": 0.07373465332507512, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9256995892113385, "min": 0.49501710490092116, "max": 1.0322851465510516, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01441370172566773, "min": 6.574286020880717e-05, "max": 0.01441370172566773, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2017918241593482, "min": 0.0008546571827144933, "max": 0.2017918241593482, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.578376045335714e-06, "min": 7.578376045335714e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001060972646347, "min": 0.0001060972646347, "max": 0.0032598644133785995, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10252609285714286, "min": 0.10252609285714286, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4353653, "min": 1.3886848, "max": 2.386621400000001, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026235667642857146, "min": 0.00026235667642857146, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036729934700000006, "min": 0.0036729934700000006, "max": 0.10868347785999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.008222191594541073, "min": 0.008222191594541073, "max": 0.45310139656066895, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.11511068046092987, "min": 0.11511068046092987, "max": 3.1717097759246826, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 407.38235294117646, "min": 407.38235294117646, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 27702.0, "min": 15984.0, "max": 32692.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.386679388473139, "min": -1.0000000521540642, "max": 1.4274547794093824, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 94.29419841617346, "min": -31.9992016851902, "max": 104.20419889688492, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.386679388473139, "min": -1.0000000521540642, "max": 1.4274547794093824, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 94.29419841617346, "min": -31.9992016851902, "max": 104.20419889688492, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.035365427908425985, "min": 0.035365427908425985, "max": 9.139126374851912, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.404849097772967, "min": 2.404849097772967, "max": 146.2260219976306, "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": "1706012879", "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": "1706015141" }, "total": 2262.5545016649994, "count": 1, "self": 0.4902757249997194, "children": { "run_training.setup": { "total": 0.04605472799994459, "count": 1, "self": 0.04605472799994459 }, "TrainerController.start_learning": { "total": 2262.0181712119997, "count": 1, "self": 1.3813547689692314, "children": { "TrainerController._reset_env": { "total": 2.7267975839999963, "count": 1, "self": 2.7267975839999963 }, "TrainerController.advance": { "total": 2257.8255118640295, "count": 63408, "self": 1.4836923580396615, "children": { "env_step": { "total": 1604.2096584340475, "count": 63408, "self": 1471.5870853090255, "children": { "SubprocessEnvManager._take_step": { "total": 131.77106760899505, "count": 63408, "self": 4.770378345037443, "children": { "TorchPolicy.evaluate": { "total": 127.00068926395761, "count": 62560, "self": 127.00068926395761 } } }, "workers": { "total": 0.8515055160269185, "count": 63408, "self": 0.0, "children": { "worker_root": { "total": 2257.007882935987, "count": 63408, "is_parallel": true, "self": 910.0214816299663, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0021057909998489777, "count": 1, "is_parallel": true, "self": 0.0005371540000851383, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015686369997638394, "count": 8, "is_parallel": true, "self": 0.0015686369997638394 } } }, "UnityEnvironment.step": { "total": 0.09588465300021198, "count": 1, "is_parallel": true, "self": 0.0006047290003152739, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00044958299986319616, "count": 1, "is_parallel": true, "self": 0.00044958299986319616 }, "communicator.exchange": { "total": 0.09311710400015727, "count": 1, "is_parallel": true, "self": 0.09311710400015727 }, "steps_from_proto": { "total": 0.0017132369998762442, "count": 1, "is_parallel": true, "self": 0.0003530999997565232, "children": { "_process_rank_one_or_two_observation": { "total": 0.001360137000119721, "count": 8, "is_parallel": true, "self": 0.001360137000119721 } } } } } } }, "UnityEnvironment.step": { "total": 1346.9864013060205, "count": 63407, "is_parallel": true, "self": 35.15715887212946, "children": { "UnityEnvironment._generate_step_input": { "total": 24.268056877908293, "count": 63407, "is_parallel": true, "self": 24.268056877908293 }, "communicator.exchange": { "total": 1188.8881983329575, "count": 63407, "is_parallel": true, "self": 1188.8881983329575 }, "steps_from_proto": { "total": 98.6729872230253, "count": 63407, "is_parallel": true, "self": 19.713285944045765, "children": { "_process_rank_one_or_two_observation": { "total": 78.95970127897954, "count": 507256, "is_parallel": true, "self": 78.95970127897954 } } } } } } } } } } }, "trainer_advance": { "total": 652.1321610719424, "count": 63408, "self": 2.6499321770334063, "children": { "process_trajectory": { "total": 127.4894906559066, "count": 63408, "self": 127.25872559090612, "children": { "RLTrainer._checkpoint": { "total": 0.2307650650004689, "count": 2, "self": 0.2307650650004689 } } }, "_update_policy": { "total": 521.9927382390024, "count": 444, "self": 313.3831575019799, "children": { "TorchPPOOptimizer.update": { "total": 208.6095807370225, "count": 22779, "self": 208.6095807370225 } } } } } } }, "trainer_threads": { "total": 8.29000782687217e-07, "count": 1, "self": 8.29000782687217e-07 }, "TrainerController._save_models": { "total": 0.08450616600021021, "count": 1, "self": 0.0014231450004444923, "children": { "RLTrainer._checkpoint": { "total": 0.08308302099976572, "count": 1, "self": 0.08308302099976572 } } } } } } }