{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3090593218803406, "min": 0.29969552159309387, "max": 1.4599910974502563, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 9252.0, "min": 9072.3828125, "max": 44290.2890625, "count": 33 }, "Pyramids.Step.mean": { "value": 989969.0, "min": 29952.0, "max": 989969.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989969.0, "min": 29952.0, "max": 989969.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5202628374099731, "min": -0.11345171183347702, "max": 0.5222572088241577, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 141.51148986816406, "min": -27.341861724853516, "max": 141.51148986816406, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.02299434319138527, "min": -0.010421034879982471, "max": 0.4460807144641876, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 6.254461288452148, "min": -2.792837381362915, "max": 105.72113037109375, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06868918770868775, "min": 0.06623856824315975, "max": 0.0735516142342293, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9616486279216285, "min": 0.5148612996396051, "max": 1.044684574531857, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014616191838978833, "min": 0.00028738573535383455, "max": 0.016489298325114334, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.20462668574570367, "min": 0.00316124308889218, "max": 0.23085017655160067, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.478968935614284e-06, "min": 7.478968935614284e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010470556509859997, "min": 0.00010470556509859997, "max": 0.0033822284725905996, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10249295714285714, "min": 0.10249295714285714, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4349014, "min": 1.3886848, "max": 2.5276197, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002590464185714285, "min": 0.0002590464185714285, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036266498599999996, "min": 0.0036266498599999996, "max": 0.11276819905999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.014492576010525227, "min": 0.014492576010525227, "max": 0.46366044878959656, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.20289605855941772, "min": 0.20289605855941772, "max": 3.2456231117248535, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 381.9125, "min": 347.70588235294116, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30553.0, "min": 15984.0, "max": 34016.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.543062483239919, "min": -1.0000000521540642, "max": 1.6287552779211718, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 123.44499865919352, "min": -30.99940161406994, "max": 138.4441986232996, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.543062483239919, "min": -1.0000000521540642, "max": 1.6287552779211718, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 123.44499865919352, "min": -30.99940161406994, "max": 138.4441986232996, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.05835482214024523, "min": 0.05438552034628468, "max": 9.965992421843112, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.668385771219619, "min": 4.515560684492812, "max": 159.45587874948978, "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": "1754780184", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1754782356" }, "total": 2171.9928126139994, "count": 1, "self": 0.48299024799962353, "children": { "run_training.setup": { "total": 0.020082340000044496, "count": 1, "self": 0.020082340000044496 }, "TrainerController.start_learning": { "total": 2171.4897400259997, "count": 1, "self": 1.3563397509824426, "children": { "TrainerController._reset_env": { "total": 2.3960660120001194, "count": 1, "self": 2.3960660120001194 }, "TrainerController.advance": { "total": 2167.6549590880168, "count": 63799, "self": 1.4016982070479571, "children": { "env_step": { "total": 1501.6006381519474, "count": 63799, "self": 1350.907628273027, "children": { "SubprocessEnvManager._take_step": { "total": 149.88941506400897, "count": 63799, "self": 4.606544288107671, "children": { "TorchPolicy.evaluate": { "total": 145.2828707759013, "count": 62559, "self": 145.2828707759013 } } }, "workers": { "total": 0.803594814911321, "count": 63799, "self": 0.0, "children": { "worker_root": { "total": 2166.63190238591, "count": 63799, "is_parallel": true, "self": 930.1250539659991, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018573540000943467, "count": 1, "is_parallel": true, "self": 0.0006166590001157601, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012406949999785866, "count": 8, "is_parallel": true, "self": 0.0012406949999785866 } } }, "UnityEnvironment.step": { "total": 0.07549244499978158, "count": 1, "is_parallel": true, "self": 0.0005474610002238478, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00044709799976772047, "count": 1, "is_parallel": true, "self": 0.00044709799976772047 }, "communicator.exchange": { "total": 0.07272639799975877, "count": 1, "is_parallel": true, "self": 0.07272639799975877 }, "steps_from_proto": { "total": 0.0017714880000312405, "count": 1, "is_parallel": true, "self": 0.0004214690006847377, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013500189993465028, "count": 8, "is_parallel": true, "self": 0.0013500189993465028 } } } } } } }, "UnityEnvironment.step": { "total": 1236.506848419911, "count": 63798, "is_parallel": true, "self": 31.819523921988093, "children": { "UnityEnvironment._generate_step_input": { "total": 23.46254703400291, "count": 63798, "is_parallel": true, "self": 23.46254703400291 }, "communicator.exchange": { "total": 1083.6366623389513, "count": 63798, "is_parallel": true, "self": 1083.6366623389513 }, "steps_from_proto": { "total": 97.58811512496868, "count": 63798, "is_parallel": true, "self": 19.489272191050077, "children": { "_process_rank_one_or_two_observation": { "total": 78.0988429339186, "count": 510384, "is_parallel": true, "self": 78.0988429339186 } } } } } } } } } } }, "trainer_advance": { "total": 664.6526227290215, "count": 63799, "self": 2.588716452013614, "children": { "process_trajectory": { "total": 128.0111472230028, "count": 63799, "self": 127.8174796690032, "children": { "RLTrainer._checkpoint": { "total": 0.19366755399960311, "count": 2, "self": 0.19366755399960311 } } }, "_update_policy": { "total": 534.052759054005, "count": 448, "self": 299.5116212890257, "children": { "TorchPPOOptimizer.update": { "total": 234.54113776497934, "count": 22869, "self": 234.54113776497934 } } } } } } }, "trainer_threads": { "total": 1.0270005077472888e-06, "count": 1, "self": 1.0270005077472888e-06 }, "TrainerController._save_models": { "total": 0.08237414799987164, "count": 1, "self": 0.001406493000104092, "children": { "RLTrainer._checkpoint": { "total": 0.08096765499976755, "count": 1, "self": 0.08096765499976755 } } } } } } }