{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.6373741626739502, "min": 0.6334901452064514, "max": 1.4763880968093872, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 19274.1953125, "min": 18741.171875, "max": 44787.7109375, "count": 33 }, "Pyramids.Step.mean": { "value": 989998.0, "min": 29952.0, "max": 989998.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989998.0, "min": 29952.0, "max": 989998.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.22272032499313354, "min": -0.10300801694393158, "max": 0.2238330990076065, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 57.46184539794922, "min": -24.824932098388672, "max": 57.46184539794922, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.030431821942329407, "min": -0.030431821942329407, "max": 0.367421418428421, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -7.851409912109375, "min": -7.851409912109375, "max": 87.07887268066406, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06790833482089166, "min": 0.06461895713031537, "max": 0.07365442090082362, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9507166874924832, "min": 0.5155809463057653, "max": 1.0450796839249246, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.011459252276836196, "min": 0.00019462852553086006, "max": 0.011459252276836196, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.16042953187570674, "min": 0.0021409137808394607, "max": 0.16042953187570674, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.3423832668571485e-06, "min": 7.3423832668571485e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010279336573600008, "min": 0.00010279336573600008, "max": 0.0031186870604376997, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10244742857142856, "min": 0.10244742857142856, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.434264, "min": 1.3886848, "max": 2.3589964000000005, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025449811428571444, "min": 0.00025449811428571444, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003562973600000002, "min": 0.003562973600000002, "max": 0.10397227376999998, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.015257926657795906, "min": 0.01466931402683258, "max": 0.3854671120643616, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.21361097693443298, "min": 0.20537039637565613, "max": 2.698269844055176, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 656.0434782608696, "min": 639.8461538461538, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30178.0, "min": 15984.0, "max": 33272.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.9525564793983231, "min": -1.0000000521540642, "max": 0.9525564793983231, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 43.817598052322865, "min": -31.999601677060127, "max": 46.72079824656248, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.9525564793983231, "min": -1.0000000521540642, "max": 0.9525564793983231, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 43.817598052322865, "min": -31.999601677060127, "max": 46.72079824656248, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.10305265652942067, "min": 0.10199728273505042, "max": 7.027245636098087, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.7404222003533505, "min": 4.385883157607168, "max": 112.43593017756939, "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": "1735571123", "python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [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 --force", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.5.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1735573831" }, "total": 2708.087514588, "count": 1, "self": 0.7459083860003375, "children": { "run_training.setup": { "total": 0.09459906399990814, "count": 1, "self": 0.09459906399990814 }, "TrainerController.start_learning": { "total": 2707.247007138, "count": 1, "self": 2.044462784022471, "children": { "TrainerController._reset_env": { "total": 3.5026701219999268, "count": 1, "self": 3.5026701219999268 }, "TrainerController.advance": { "total": 2701.619903483978, "count": 63226, "self": 2.0823131560450747, "children": { "env_step": { "total": 1734.705533780952, "count": 63226, "self": 1594.4621142209135, "children": { "SubprocessEnvManager._take_step": { "total": 139.01794505901626, "count": 63226, "self": 5.741377828999475, "children": { "TorchPolicy.evaluate": { "total": 133.27656723001678, "count": 62558, "self": 133.27656723001678 } } }, "workers": { "total": 1.2254745010221768, "count": 63226, "self": 0.0, "children": { "worker_root": { "total": 2701.057886568959, "count": 63226, "is_parallel": true, "self": 1257.3386714489097, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005429410000033386, "count": 1, "is_parallel": true, "self": 0.0009378129999504381, "children": { "_process_rank_one_or_two_observation": { "total": 0.0044915970000829475, "count": 8, "is_parallel": true, "self": 0.0044915970000829475 } } }, "UnityEnvironment.step": { "total": 0.10294719199998781, "count": 1, "is_parallel": true, "self": 0.0007856630002152087, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005131349998919177, "count": 1, "is_parallel": true, "self": 0.0005131349998919177 }, "communicator.exchange": { "total": 0.09750259599991296, "count": 1, "is_parallel": true, "self": 0.09750259599991296 }, "steps_from_proto": { "total": 0.004145797999967726, "count": 1, "is_parallel": true, "self": 0.000423678000174732, "children": { "_process_rank_one_or_two_observation": { "total": 0.0037221199997929943, "count": 8, "is_parallel": true, "self": 0.0037221199997929943 } } } } } } }, "UnityEnvironment.step": { "total": 1443.7192151200493, "count": 63225, "is_parallel": true, "self": 43.96181901400928, "children": { "UnityEnvironment._generate_step_input": { "total": 27.932565640043663, "count": 63225, "is_parallel": true, "self": 27.932565640043663 }, "communicator.exchange": { "total": 1250.817062214013, "count": 63225, "is_parallel": true, "self": 1250.817062214013 }, "steps_from_proto": { "total": 121.0077682519834, "count": 63225, "is_parallel": true, "self": 25.852461573077107, "children": { "_process_rank_one_or_two_observation": { "total": 95.1553066789063, "count": 505800, "is_parallel": true, "self": 95.1553066789063 } } } } } } } } } } }, "trainer_advance": { "total": 964.8320565469807, "count": 63226, "self": 3.608022636974283, "children": { "process_trajectory": { "total": 149.67713122801115, "count": 63226, "self": 149.42917199701105, "children": { "RLTrainer._checkpoint": { "total": 0.24795923100009531, "count": 2, "self": 0.24795923100009531 } } }, "_update_policy": { "total": 811.5469026819952, "count": 438, "self": 347.83861224100326, "children": { "TorchPPOOptimizer.update": { "total": 463.70829044099196, "count": 22857, "self": 463.70829044099196 } } } } } } }, "trainer_threads": { "total": 1.216999862663215e-06, "count": 1, "self": 1.216999862663215e-06 }, "TrainerController._save_models": { "total": 0.07996953099973325, "count": 1, "self": 0.002366009000070335, "children": { "RLTrainer._checkpoint": { "total": 0.07760352199966292, "count": 1, "self": 0.07760352199966292 } } } } } } }