.. |
atari-sac.yaml
|
52c94b7ee9
[RLlib] Allow SAC to use custom models as Q- or policy nets and deprecate "state-preprocessor" for image spaces. (#13522)
|
3 年之前 |
cartpole-continuous-pybullet-sac.yaml
|
e98808ce11
[RLlib] Fix 2 flakey test cases. (#14892)
|
3 年之前 |
cartpole-sac.yaml
|
af8a93f2a4
Deflake some RLlib tests (#14947)
|
3 年之前 |
halfcheetah-pybullet-sac.yaml
|
e3e6ed7aaa
[RLlib] Issues 17844, 18034: Fix n-step > 1 bug. (#18358)
|
3 年之前 |
halfcheetah-sac.yaml
|
2746fc0476
[RLlib] Auto-framework, retire `use_pytorch` in favor of `framework=...` (#8520)
|
4 年之前 |
mspacman-sac.yaml
|
52c94b7ee9
[RLlib] Allow SAC to use custom models as Q- or policy nets and deprecate "state-preprocessor" for image spaces. (#13522)
|
3 年之前 |
pendulum-sac-fake-gpus.yaml
|
63db0e3a7c
[RLlib] Fix SAC learning test flakiness introduced in PR: "Sub-class `Trainer` (instead of `build_trainer()`): All remaining classes; soft-deprecate `build_trainer`." (#20985)
|
2 年之前 |
pendulum-sac.yaml
|
026bf01071
[RLlib] Upgrade gym version to 0.21 and deprecate pendulum-v0. (#19535)
|
3 年之前 |
pendulum-transformed-actions-sac.yaml
|
63db0e3a7c
[RLlib] Fix SAC learning test flakiness introduced in PR: "Sub-class `Trainer` (instead of `build_trainer()`): All remaining classes; soft-deprecate `build_trainer`." (#20985)
|
2 年之前 |