Eric Liang
|
3febc5e107
[data] Revert the dataset to datastream class rename (#35082)
|
1 年之前 |
Jiajun Yao
|
e73eba20af
[docs] Fix broken links (#34665)
|
1 年之前 |
Eric Liang
|
c0dff99a03
[data] [docs] Datastream docs rename [5/n] (#34512)
|
1 年之前 |
Sven Mika
|
d429363a47
[RLlib] [RELEASE BLOCKER] Fix RLlib CLI: e.g. `rllib example run cartpole-ppo` fails. (#30664)
|
1 年之前 |
Sven Mika
|
9ece8acb0c
[RLlib] Docs update: New Algorithm checkpoints, Policy checkpoints and Policy model exports in native format (#28812)
|
2 年之前 |
kourosh hakhamaneshi
|
5779ee764d
[RLlib] Fix ope v_gain (#28136)
|
2 年之前 |
Rohan Potdar
|
600b8d4729
[RLlib]: Fix OPE docs. (#27460)
|
2 年之前 |
Rohan Potdar
|
deccf33912
[RLlib]: Add Off-Policy Estimation docs (#26809)
|
2 年之前 |
Rohan Potdar
|
09ce4711fd
[RLlib]: Move OPE to evaluation config (#25911)
|
2 年之前 |
Sven Mika
|
130b7eeaba
[RLlib] `Trainer` to `Algorithm` renaming. (#25539)
|
2 年之前 |
Rohan Potdar
|
a9d8da0100
[RLlib]: Doubly Robust Off-Policy Evaluation. (#25056)
|
2 年之前 |
Sven Mika
|
a559efb7e4
[CI; LinkCheck] 3 RLlib fixes. (#25476)
|
2 年之前 |
Sven Mika
|
b5bc2b93c3
[RLlib] Move all remaining algos into `algorithms` directory. (#25366)
|
2 年之前 |
Yi Cheng
|
fd0f967d2e
Revert "[RLlib] Move (A/DD)?PPO and IMPALA algos to `algorithms` dir and rename policy and trainer classes. (#25346)" (#25420)
|
2 年之前 |
Sven Mika
|
e4ceae19ef
[RLlib] Move (A/DD)?PPO and IMPALA algos to `algorithms` dir and rename policy and trainer classes. (#25346)
|
2 年之前 |
Rohan Potdar
|
ab81c8e9ca
[RLlib]: Rename `input_evaluation` to `off_policy_estimation_methods`. (#25107)
|
2 年之前 |
Steven Morad
|
501d932449
[RLlib] SAC, RNNSAC, and CQL TrainerConfig objects (#25059)
|
2 年之前 |
Christy Bergman
|
76eb47e226
[RLlib; docs] Rename UCB -> LinUCB. (#24348)
|
2 年之前 |
Sven Mika
|
5b61a00792
[RLlib] Feed all values in COMMON_CONFIG directly from TrainerConfig() (removes duplicate values and comments). (#24433)
|
2 年之前 |
Jeroen Bédorf
|
1263015931
[RLlib] Add support for writing env 'info' dicts to output datasets for TFPolicies (for TorchPolicies, these are part of the view-requirements by default and thus written either way). (#24041)
|
2 年之前 |
Max Pumperla
|
11c40e363d
[docs] external promo content (#22823)
|
2 年之前 |
Max Pumperla
|
9482f03134
[docs] RLlib concepts consolidation, user guide, RL conf prep (#22496)
|
2 年之前 |
Jun Gong
|
6f5afcbce9
[RLlib] Docs enhancements: Setup-dev instructions; Ray datasets integration. (#22239)
|
2 年之前 |
Max Pumperla
|
f9b71a8bf6
[docs] new structure (#21776)
|
2 年之前 |