| .. |
|
halfcheetah-ddpg.yaml
|
[RLlib] Replay Buffer API and Ape-X. (#24506)
|
2022-05-17 13:43:49 +02:00 |
|
halfcheetah-pybullet-ddpg.yaml
|
[RLlib] Replay Buffer API and Ape-X. (#24506)
|
2022-05-17 13:43:49 +02:00 |
|
hopper-pybullet-ddpg.yaml
|
[RLlib] Replay Buffer API and Ape-X. (#24506)
|
2022-05-17 13:43:49 +02:00 |
|
invertedpendulum-td3.yaml
|
[RLlib] Replay Buffer API and Ape-X. (#24506)
|
2022-05-17 13:43:49 +02:00 |
|
memory-leak-test-ddpg.yaml
|
[RLlib] Replay Buffer API and Ape-X. (#24506)
|
2022-05-17 13:43:49 +02:00 |
|
mountaincarcontinuous-apex-ddpg.yaml
|
[RLlib] Auto-framework, retire use_pytorch in favor of framework=... (#8520)
|
2020-05-27 16:19:13 +02:00 |
|
mountaincarcontinuous-ddpg.yaml
|
[RLlib] Replay Buffer API and Ape-X. (#24506)
|
2022-05-17 13:43:49 +02:00 |
|
mujoco-td3.yaml
|
[RLlib] Replay Buffer API and Ape-X. (#24506)
|
2022-05-17 13:43:49 +02:00 |
|
pendulum-apex-ddpg.yaml
|
[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 |
|
pendulum-ddpg-fake-gpus.yaml
|
[RLlib] Replay Buffer API and Ape-X. (#24506)
|
2022-05-17 13:43:49 +02:00 |
|
pendulum-ddpg.yaml
|
[RLlib] Replay Buffer API and Ape-X. (#24506)
|
2022-05-17 13:43:49 +02:00 |
|
pendulum-td3-fake-gpus.yaml
|
[RLlib] Replay Buffer API and Ape-X. (#24506)
|
2022-05-17 13:43:49 +02:00 |
|
pendulum-td3.yaml
|
[RLlib] Replay Buffer API and Ape-X. (#24506)
|
2022-05-17 13:43:49 +02:00 |
