{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.647111177444458, "min": 0.647111177444458, "max": 1.5848090648651123, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 19164.84375, "min": 19068.0, "max": 49141.7578125, "count": 33 }, "Pyramids.Step.mean": { "value": 989963.0, "min": 29952.0, "max": 989963.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989963.0, "min": 29952.0, "max": 989963.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.9198499917984009, "min": -0.16273945569992065, "max": 0.9491987824440002, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 259.397705078125, "min": -39.70842742919922, "max": 271.85845947265625, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.02175263687968254, "min": -0.006435431074351072, "max": 0.22001469135284424, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 6.134243488311768, "min": -1.7246955633163452, "max": 52.14348220825195, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06944564018729311, "min": 0.06646719624768593, "max": 0.07530439315001583, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.4861194813110518, "min": 0.273545203622133, "max": 0.5794674223876483, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.010973609691780328, "min": 0.0002696208207550155, "max": 0.012621592977666296, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.0768152678424623, "min": 0.0015524853859694827, "max": 0.09922974393603826, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.391111822042856e-06, "min": 7.391111822042856e-06, "max": 0.00029544960151679995, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 5.173778275429999e-05, "min": 5.173778275429999e-05, "max": 0.0016264381578540005, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10246367142857145, "min": 0.10246367142857145, "max": 0.1984832, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 0.7172457000000001, "min": 0.7172457000000001, "max": 1.276217, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002561207757142857, "min": 0.0002561207757142857, "max": 0.00984847168, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.00179284543, "min": 0.00179284543, "max": 0.054230385400000004, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.007866989821195602, "min": 0.007866989821195602, "max": 0.2532063126564026, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.05506892874836922, "min": 0.05506892874836922, "max": 1.0128252506256104, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 341.7608695652174, "min": 281.8333333333333, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31442.0, "min": 15984.0, "max": 32500.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5834555385841265, "min": -1.0000000521540642, "max": 1.6939422910173352, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 142.51099847257137, "min": -32.000001668930054, "max": 176.16999826580286, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5834555385841265, "min": -1.0000000521540642, "max": 1.6939422910173352, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 142.51099847257137, "min": -32.000001668930054, "max": 176.16999826580286, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.02894392934346494, "min": 0.0247106769309959, "max": 6.708137252833694, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.6049536409118446, "min": 2.3211749119241176, "max": 107.33019604533911, "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": "1716471412", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "command_line_arguments": "/media/fast/code/learning/venv_learning/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": "2.3.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1716472491" }, "total": 1078.3966970620677, "count": 1, "self": 0.37061663111671805, "children": { "run_training.setup": { "total": 0.14060499100014567, "count": 1, "self": 0.14060499100014567 }, "TrainerController.start_learning": { "total": 1077.8854754399508, "count": 1, "self": 1.2692033905768767, "children": { "TrainerController._reset_env": { "total": 1.9787482819519937, "count": 1, "self": 1.9787482819519937 }, "TrainerController.advance": { "total": 1074.5928020253778, "count": 63797, "self": 0.6466538163367659, "children": { "env_step": { "total": 1073.946148209041, "count": 63797, "self": 825.9957018948626, "children": { "SubprocessEnvManager._take_step": { "total": 247.3071386073716, "count": 63797, "self": 3.3293473498197272, "children": { "TorchPolicy.evaluate": { "total": 243.97779125755187, "count": 62571, "self": 243.97779125755187 } } }, "workers": { "total": 0.6433077068068087, "count": 63797, "self": 0.0, "children": { "worker_root": { "total": 1076.647762586479, "count": 63797, "is_parallel": true, "self": 629.7173935208702, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0010522620286792517, "count": 1, "is_parallel": true, "self": 0.0004501680377870798, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006020939908921719, "count": 8, "is_parallel": true, "self": 0.0006020939908921719 } } }, "UnityEnvironment.step": { "total": 0.020503623061813414, "count": 1, "is_parallel": true, "self": 0.00019388401415199041, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00017534801736474037, "count": 1, "is_parallel": true, "self": 0.00017534801736474037 }, "communicator.exchange": { "total": 0.019491384970024228, "count": 1, "is_parallel": true, "self": 0.019491384970024228 }, "steps_from_proto": { "total": 0.0006430060602724552, "count": 1, "is_parallel": true, "self": 0.00016678415704518557, "children": { "_process_rank_one_or_two_observation": { "total": 0.00047622190322726965, "count": 8, "is_parallel": true, "self": 0.00047622190322726965 } } } } } } }, "UnityEnvironment.step": { "total": 446.93036906560883, "count": 63796, "is_parallel": true, "self": 11.7354813052807, "children": { "UnityEnvironment._generate_step_input": { "total": 8.596135839819908, "count": 63796, "is_parallel": true, "self": 8.596135839819908 }, "communicator.exchange": { "total": 392.5191468523117, "count": 63796, "is_parallel": true, "self": 392.5191468523117 }, "steps_from_proto": { "total": 34.07960506819654, "count": 63796, "is_parallel": true, "self": 8.149204221437685, "children": { "_process_rank_one_or_two_observation": { "total": 25.930400846758857, "count": 510368, "is_parallel": true, "self": 25.930400846758857 } } } } } } } } } } } } }, "trainer_threads": { "total": 5.9850048273801804e-05, "count": 1, "self": 5.9850048273801804e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 1075.5654371996643, "count": 89510, "is_parallel": true, "self": 0.9147835909388959, "children": { "process_trajectory": { "total": 356.63685560494196, "count": 89510, "is_parallel": true, "self": 356.36787491699215, "children": { "RLTrainer._checkpoint": { "total": 0.26898068794980645, "count": 2, "is_parallel": true, "self": 0.26898068794980645 } } }, "_update_policy": { "total": 718.0137980037834, "count": 223, "is_parallel": true, "self": 328.22454430977814, "children": { "TorchPPOOptimizer.update": { "total": 389.7892536940053, "count": 30760, "is_parallel": true, "self": 389.7892536940053 } } } } } } } } }, "TrainerController._save_models": { "total": 0.04466189199592918, "count": 1, "self": 0.0010206070728600025, "children": { "RLTrainer._checkpoint": { "total": 0.04364128492306918, "count": 1, "self": 0.04364128492306918 } } } } } } }