{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.326335072517395, "min": 0.3076534569263458, "max": 1.4244384765625, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 9842.265625, "min": 9293.595703125, "max": 43211.765625, "count": 33 }, "Pyramids.Step.mean": { "value": 989972.0, "min": 29952.0, "max": 989972.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989972.0, "min": 29952.0, "max": 989972.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.577602207660675, "min": -0.10177814960479736, "max": 0.6359911561012268, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 158.26300048828125, "min": -24.528533935546875, "max": 179.34950256347656, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.0090751051902771, "min": 0.00823266338557005, "max": 0.3039073348045349, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 2.4865787029266357, "min": 2.31337833404541, "max": 73.24166870117188, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07137275389692399, "min": 0.06481252703954289, "max": 0.07409159096043637, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0705913084538599, "min": 0.4986033534006237, "max": 1.073211593417606, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016380058156571415, "min": 0.0013198343651070466, "max": 0.017826159357426544, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.24570087234857124, "min": 0.017157846746391606, "max": 0.25205220984935295, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.4677775107733324e-06, "min": 7.4677775107733324e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011201666266159998, "min": 0.00011201666266159998, "max": 0.0036331714889428998, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10248922666666668, "min": 0.10248922666666668, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5373384000000003, "min": 1.3886848, "max": 2.6110571, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025867374399999996, "min": 0.00025867374399999996, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0038801061599999993, "min": 0.0038801061599999993, "max": 0.12112460429, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01273871585726738, "min": 0.01273871585726738, "max": 0.4379827380180359, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1910807341337204, "min": 0.18109068274497986, "max": 3.0658791065216064, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 352.7294117647059, "min": 298.81, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29982.0, "min": 15984.0, "max": 32688.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.575641839136911, "min": -1.0000000521540642, "max": 1.698287109484767, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 135.50519816577435, "min": -30.669401668012142, "max": 171.52699805796146, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.575641839136911, "min": -1.0000000521540642, "max": 1.698287109484767, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 135.50519816577435, "min": -30.669401668012142, "max": 171.52699805796146, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04741224251433038, "min": 0.03910364805558471, "max": 8.216762250289321, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.077452856232412, "min": 3.871261157502886, "max": 131.46819600462914, "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": "1683664976", "python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [GCC 9.4.0]", "command_line_arguments": "/home/mark/rl_course/.unit5_venv/bin/mlagents-learn ./ml-agents/config/ppo/PyramidsRND.yaml --env=./ml-agents/training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids1 --no-graphics", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1683667412" }, "total": 2435.7594889309257, "count": 1, "self": 0.37448126869276166, "children": { "run_training.setup": { "total": 0.014408939983695745, "count": 1, "self": 0.014408939983695745 }, "TrainerController.start_learning": { "total": 2435.3705987222493, "count": 1, "self": 1.3832748336717486, "children": { "TrainerController._reset_env": { "total": 5.0853781080804765, "count": 1, "self": 5.0853781080804765 }, "TrainerController.advance": { "total": 2428.7854363461956, "count": 64088, "self": 1.2597052305936813, "children": { "env_step": { "total": 1526.1699736723676, "count": 64088, "self": 1426.5914449468255, "children": { "SubprocessEnvManager._take_step": { "total": 98.66571643296629, "count": 64088, "self": 4.184799485839903, "children": { "TorchPolicy.evaluate": { "total": 94.48091694712639, "count": 62562, "self": 94.48091694712639 } } }, "workers": { "total": 0.9128122925758362, "count": 64088, "self": 0.0, "children": { "worker_root": { "total": 2432.4824393284507, "count": 64088, "is_parallel": true, "self": 1119.5973049402237, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005489129573106766, "count": 1, "is_parallel": true, "self": 0.0010839742608368397, "children": { "_process_rank_one_or_two_observation": { "total": 0.004405155312269926, "count": 8, "is_parallel": true, "self": 0.004405155312269926 } } }, "UnityEnvironment.step": { "total": 0.039962745271623135, "count": 1, "is_parallel": true, "self": 0.0013755708932876587, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0010408447124063969, "count": 1, "is_parallel": true, "self": 0.0010408447124063969 }, "communicator.exchange": { "total": 0.03430226491764188, "count": 1, "is_parallel": true, "self": 0.03430226491764188 }, "steps_from_proto": { "total": 0.003244064748287201, "count": 1, "is_parallel": true, "self": 0.00045220181345939636, "children": { "_process_rank_one_or_two_observation": { "total": 0.0027918629348278046, "count": 8, "is_parallel": true, "self": 0.0027918629348278046 } } } } } } }, "UnityEnvironment.step": { "total": 1312.885134388227, "count": 64087, "is_parallel": true, "self": 83.23179650492966, "children": { "UnityEnvironment._generate_step_input": { "total": 31.63614310370758, "count": 64087, "is_parallel": true, "self": 31.63614310370758 }, "communicator.exchange": { "total": 986.4183079693466, "count": 64087, "is_parallel": true, "self": 986.4183079693466 }, "steps_from_proto": { "total": 211.59888681024313, "count": 64087, "is_parallel": true, "self": 30.572862019296736, "children": { "_process_rank_one_or_two_observation": { "total": 181.0260247909464, "count": 512696, "is_parallel": true, "self": 181.0260247909464 } } } } } } } } } } }, "trainer_advance": { "total": 901.3557574432343, "count": 64088, "self": 2.5509371641092002, "children": { "process_trajectory": { "total": 122.45769395586103, "count": 64088, "self": 122.21148914797232, "children": { "RLTrainer._checkpoint": { "total": 0.24620480788871646, "count": 2, "self": 0.24620480788871646 } } }, "_update_policy": { "total": 776.3471263232641, "count": 453, "self": 514.9720018105581, "children": { "TorchPPOOptimizer.update": { "total": 261.37512451270595, "count": 22761, "self": 261.37512451270595 } } } } } } }, "trainer_threads": { "total": 1.225154846906662e-06, "count": 1, "self": 1.225154846906662e-06 }, "TrainerController._save_models": { "total": 0.11650820914655924, "count": 1, "self": 0.0010827700607478619, "children": { "RLTrainer._checkpoint": { "total": 0.11542543908581138, "count": 1, "self": 0.11542543908581138 } } } } } } }