{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.15660691261291504, "min": 0.1543264091014862, "max": 1.4410406351089478, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 4720.7587890625, "min": 4577.9384765625, "max": 43715.41015625, "count": 100 }, "Pyramids.Step.mean": { "value": 2999894.0, "min": 29878.0, "max": 2999894.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999894.0, "min": 29878.0, "max": 2999894.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.8098756670951843, "min": -0.13551738858222961, "max": 0.8292228579521179, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 242.15283203125, "min": -32.11762237548828, "max": 244.62074279785156, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.0029834385495632887, "min": -0.0501549206674099, "max": 0.5536719560623169, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 0.8920481204986572, "min": -14.394462585449219, "max": 131.2202606201172, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06912912183260131, "min": 0.0635057190388796, "max": 0.07331064539806295, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0369368274890196, "min": 0.5410115727728964, "max": 1.0996596809709442, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01566997717889452, "min": 0.0010214739307312422, "max": 0.017609723939261, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2350496576834178, "min": 0.014300635030237391, "max": 0.2613465759980803, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.4780528406822237e-06, "min": 1.4780528406822237e-06, "max": 0.00029840312553229163, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.2170792610233356e-05, "min": 2.2170792610233356e-05, "max": 0.004010801663066133, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10049265111111112, "min": 0.10049265111111112, "max": 0.19946770833333333, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.507389766666667, "min": 1.4210677, "max": 2.7676113666666664, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 5.9215846000000057e-05, "min": 5.9215846000000057e-05, "max": 0.009946824062500002, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.0008882376900000009, "min": 0.0008882376900000009, "max": 0.13369969328, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.006883983034640551, "min": 0.006577217020094395, "max": 0.3836733102798462, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.10325974225997925, "min": 0.09306111931800842, "max": 3.0693864822387695, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 241.13178294573643, "min": 203.00704225352112, "max": 992.78125, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31106.0, "min": 16549.0, "max": 32535.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6968325453326685, "min": -0.9262121748743635, "max": 1.7971560139182612, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 218.89139834791422, "min": -30.565001770853996, "max": 253.39899796247482, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6968325453326685, "min": -0.9262121748743635, "max": 1.7971560139182612, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 218.89139834791422, "min": -30.565001770853996, "max": 253.39899796247482, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.017319782374109964, "min": 0.015489275331822792, "max": 7.435108531923855, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 2.2342519262601854, "min": 1.9973908661704627, "max": 126.39684504270554, "count": 100 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1692462164", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "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": "1692467259" }, "total": 5095.324234156, "count": 1, "self": 0.3718634770011704, "children": { "run_training.setup": { "total": 0.0401019319997431, "count": 1, "self": 0.0401019319997431 }, "TrainerController.start_learning": { "total": 5094.912268746999, "count": 1, "self": 3.9007297858315724, "children": { "TrainerController._reset_env": { "total": 4.1704980669996985, "count": 1, "self": 4.1704980669996985 }, "TrainerController.advance": { "total": 5086.744691613169, "count": 195066, "self": 3.802885274836626, "children": { "env_step": { "total": 3335.752153585221, "count": 195066, "self": 3038.242674998514, "children": { "SubprocessEnvManager._take_step": { "total": 295.2548055177199, "count": 195066, "self": 12.785866159723355, "children": { "TorchPolicy.evaluate": { "total": 282.46893935799653, "count": 187567, "self": 282.46893935799653 } } }, "workers": { "total": 2.2546730689873584, "count": 195066, "self": 0.0, "children": { "worker_root": { "total": 5088.258120456057, "count": 195066, "is_parallel": true, "self": 2316.3693697151625, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018431530002089858, "count": 1, "is_parallel": true, "self": 0.0005897220007682336, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012534309994407522, "count": 8, "is_parallel": true, "self": 0.0012534309994407522 } } }, "UnityEnvironment.step": { "total": 0.0353608410000561, "count": 1, "is_parallel": true, "self": 0.0003550189999259601, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00034493699968152214, "count": 1, "is_parallel": true, "self": 0.00034493699968152214 }, "communicator.exchange": { "total": 0.03345642100020996, "count": 1, "is_parallel": true, "self": 0.03345642100020996 }, "steps_from_proto": { "total": 0.0012044640002386586, "count": 1, "is_parallel": true, "self": 0.0002618370008349302, "children": { "_process_rank_one_or_two_observation": { "total": 0.0009426269994037284, "count": 8, "is_parallel": true, "self": 0.0009426269994037284 } } } } } } }, "UnityEnvironment.step": { "total": 2771.888750740895, "count": 195065, "is_parallel": true, "self": 64.86174442401352, "children": { "UnityEnvironment._generate_step_input": { "total": 45.15624508510473, "count": 195065, "is_parallel": true, "self": 45.15624508510473 }, "communicator.exchange": { "total": 2467.6241169218174, "count": 195065, "is_parallel": true, "self": 2467.6241169218174 }, "steps_from_proto": { "total": 194.24664430995927, "count": 195065, "is_parallel": true, "self": 39.582233558300686, "children": { "_process_rank_one_or_two_observation": { "total": 154.66441075165858, "count": 1560520, "is_parallel": true, "self": 154.66441075165858 } } } } } } } } } } }, "trainer_advance": { "total": 1747.1896527531121, "count": 195066, "self": 7.79327306197365, "children": { "process_trajectory": { "total": 299.964351471177, "count": 195066, "self": 299.32158444917786, "children": { "RLTrainer._checkpoint": { "total": 0.6427670219991342, "count": 6, "self": 0.6427670219991342 } } }, "_update_policy": { "total": 1439.4320282199615, "count": 1406, "self": 906.0985546589145, "children": { "TorchPPOOptimizer.update": { "total": 533.333473561047, "count": 68337, "self": 533.333473561047 } } } } } } }, "trainer_threads": { "total": 9.849991329247132e-07, "count": 1, "self": 9.849991329247132e-07 }, "TrainerController._save_models": { "total": 0.09634829599963268, "count": 1, "self": 0.0015519450007559499, "children": { "RLTrainer._checkpoint": { "total": 0.09479635099887673, "count": 1, "self": 0.09479635099887673 } } } } } } }