Sven Mika e2edca45d4 [RLlib] PPO torch memory leak and unnecessary torch.Tensor creation and gc'ing. (#7238) ... * Take out stats to analyze memory leak in torch PPO. * WIP * WIP * WIP * WIP * WIP * WIP. * WIP. * WIP. * WIP. * WIP. * WIP. * WIP. * WIP. * WIP. * WIP. * WIP. * WIP. * WIP. * WIP. * WIP. * WIP. * WIP. * WIP. * WIP. * WIP. * WIP. * LINT. * Fix determine_tests_to_run.py. * minor change to re-test after determine_tests_to_run.py. * LINT. * update comments. * WIP * WIP * WIP * FIX. * Fix sequence_mask being dependent on torch being installed. * Fix strange ray-core tf-error in test_memory_scheduling test case. * Fix strange ray-core tf-error in test_memory_scheduling test case. * Fix strange ray-core tf-error in test_memory_scheduling test case. * Fix strange ray-core tf-error in test_memory_scheduling test case.		2020-02-22 11:02:31 -08:00
..
exploration	[RLlib] PPO torch memory leak and unnecessary torch.Tensor creation and gc'ing. (#7238)	2020-02-22 11:02:31 -08:00
schedules	[RLlib] Exploration API: merge deterministic flag with exploration classes (SoftQ and StochasticSampling). (#7155)	2020-02-19 12:18:45 -08:00
tests	[RLlib] Exploration API: merge deterministic flag with exploration classes (SoftQ and StochasticSampling). (#7155)	2020-02-19 12:18:45 -08:00
__init__.py	[RLlib] Exploration API (+EpsilonGreedy sub-class). (#6974)	2020-02-10 15:22:07 -08:00
actors.py	[rllib] - TaskPool.completed_prefetch() no longer returns stale object ids after an error (#7139)	2020-02-13 22:30:44 -08:00
annotations.py	Remove future imports (#6724)	2020-01-09 00:15:48 -08:00
compression.py	Stop vendoring pyarrow (#7233)	2020-02-19 19:01:26 -08:00
debug.py	Remove future imports (#6724)	2020-01-09 00:15:48 -08:00
deprecation.py	[RLlib] Exploration API: merge deterministic flag with exploration classes (SoftQ and StochasticSampling). (#7155)	2020-02-19 12:18:45 -08:00
error.py	Remove future imports (#6724)	2020-01-09 00:15:48 -08:00
experimental_dsl.py	[rllib] [experimental] custom RL training pipelines (PG_pl, A2C_pl) (#7213)	2020-02-19 16:07:37 -08:00
explained_variance.py	[RLlib] Implement PPO torch version. (#6826)	2020-01-20 23:06:50 -08:00
filter.py	Remove future imports (#6724)	2020-01-09 00:15:48 -08:00
filter_manager.py	Remove future imports (#6724)	2020-01-09 00:15:48 -08:00
framework.py	[RLlib] Exploration API: merge deterministic flag with exploration classes (SoftQ and StochasticSampling). (#7155)	2020-02-19 12:18:45 -08:00
from_config.py	Fix various issues/warnings that come up on Jenkins (#7147)	2020-02-17 16:08:55 -08:00
memory.py	Remove future imports (#6724)	2020-01-09 00:15:48 -08:00
numpy.py	Remove future imports (#6724)	2020-01-09 00:15:48 -08:00
policy_client.py	Remove future imports (#6724)	2020-01-09 00:15:48 -08:00
policy_server.py	Remove future imports (#6724)	2020-01-09 00:15:48 -08:00
seed.py	Remove future imports (#6724)	2020-01-09 00:15:48 -08:00
sgd.py	[RLlib] Exploration API: merge deterministic flag with exploration classes (SoftQ and StochasticSampling). (#7155)	2020-02-19 12:18:45 -08:00
test_utils.py	[RLlib] PPO torch memory leak and unnecessary torch.Tensor creation and gc'ing. (#7238)	2020-02-22 11:02:31 -08:00
tf_ops.py	Remove future imports (#6724)	2020-01-09 00:15:48 -08:00
tf_run_builder.py	Remove future imports (#6724)	2020-01-09 00:15:48 -08:00
timer.py	Remove future imports (#6724)	2020-01-09 00:15:48 -08:00
torch_ops.py	[RLlib] PPO torch memory leak and unnecessary torch.Tensor creation and gc'ing. (#7238)	2020-02-22 11:02:31 -08:00
tracking_dict.py	Remove future imports (#6724)	2020-01-09 00:15:48 -08:00
tuple_actions.py	[RLlib] Exploration API: merge deterministic flag with exploration classes (SoftQ and StochasticSampling). (#7155)	2020-02-19 12:18:45 -08:00
window_stat.py	Remove future imports (#6724)	2020-01-09 00:15:48 -08:00