| .. |
|
a3c
|
[RLlib] Trainer sub-class A2C/A3C (instead of build_trainer). (#20635)
|
2021-11-24 22:07:13 +01:00 |
|
ars
|
[RLlib] Sub-class Trainer (instead of build_trainer()): All remaining classes; soft-deprecate build_trainer. (#20725)
|
2021-12-04 22:05:26 +01:00 |
|
cql
|
[RLLib] Fix deprecated convert_to_non_torch_type (#20751)
|
2021-12-09 14:42:12 +01:00 |
|
ddpg
|
[RLlib] Allow for evaluation to run by timesteps (alternative to episodes) and add auto-setting to make sure train doesn't ever have to wait for eval (e.g. long episodes) to finish. (#20757)
|
2021-12-04 13:26:33 +01:00 |
|
dqn
|
[RLlib] Fix SAC learning test flakiness introduced in PR: "Sub-class Trainer (instead of build_trainer()): All remaining classes; soft-deprecate build_trainer." (#20985)
|
2021-12-09 14:24:27 +01:00 |
|
dreamer
|
[RLlib] Sub-class Trainer (instead of build_trainer()): All remaining classes; soft-deprecate build_trainer. (#20725)
|
2021-12-04 22:05:26 +01:00 |
|
es
|
[RLlib] Sub-class Trainer (instead of build_trainer()): All remaining classes; soft-deprecate build_trainer. (#20725)
|
2021-12-04 22:05:26 +01:00 |
|
impala
|
[RLlib] Trainer sub-class IMPALA (instead of using build_trainer()). (#20570)
|
2021-11-30 19:08:36 +01:00 |
|
maml
|
[RLlib] Rename metrics_smoothing_episodes into metrics_num_episodes_for_smoothing for clarity. (#20983)
|
2021-12-11 20:33:35 +01:00 |
|
marwil
|
[RLlib] Sub-class Trainer (instead of build_trainer()): All remaining classes; soft-deprecate build_trainer. (#20725)
|
2021-12-04 22:05:26 +01:00 |
|
mbmpo
|
[RLlib] Sub-class Trainer (instead of build_trainer()): All remaining classes; soft-deprecate build_trainer. (#20725)
|
2021-12-04 22:05:26 +01:00 |
|
pg
|
[RLlib] Trainer sub-class PPO/DDPPO (instead of build_trainer()). (#20571)
|
2021-11-23 23:01:05 +01:00 |
|
ppo
|
[RLlib] Trainer sub-class PPO/DDPPO (instead of build_trainer()). (#20571)
|
2021-11-23 23:01:05 +01:00 |
|
qmix
|
[RLlib] Sub-class Trainer (instead of build_trainer()): All remaining classes; soft-deprecate build_trainer. (#20725)
|
2021-12-04 22:05:26 +01:00 |
|
sac
|
[RLlib] Sub-class Trainer (instead of build_trainer()): All remaining classes; soft-deprecate build_trainer. (#20725)
|
2021-12-04 22:05:26 +01:00 |
|
slateq
|
[RLlib] Sub-class Trainer (instead of build_trainer()): All remaining classes; soft-deprecate build_trainer. (#20725)
|
2021-12-04 22:05:26 +01:00 |
|
tests
|
[RLlib] Allow for evaluation to run by timesteps (alternative to episodes) and add auto-setting to make sure train doesn't ever have to wait for eval (e.g. long episodes) to finish. (#20757)
|
2021-12-04 13:26:33 +01:00 |
|
__init__.py
|
[RLlib] Fixing Memory Leak In Multi-Agent environments. Adding tooling for finding memory leaks in workers. (#15815)
|
2021-05-18 13:23:00 +02:00 |
|
callbacks.py
|
[RLlib] Support for RE3 exploration algorithm (for tf) (#19551)
|
2021-12-07 13:26:34 +01:00 |
|
mock.py
|
[RLlib] Trainer sub-class PPO/DDPPO (instead of build_trainer()). (#20571)
|
2021-11-23 23:01:05 +01:00 |
|
registry.py
|
[RLlib] Trainer sub-class PPO/DDPPO (instead of build_trainer()). (#20571)
|
2021-11-23 23:01:05 +01:00 |
|
trainer.py
|
[RLlib] Rename metrics_smoothing_episodes into metrics_num_episodes_for_smoothing for clarity. (#20983)
|
2021-12-11 20:33:35 +01:00 |
|
trainer_template.py
|
[RLlib] Sub-class Trainer (instead of build_trainer()): All remaining classes; soft-deprecate build_trainer. (#20725)
|
2021-12-04 22:05:26 +01:00 |
