gjoliver
|
9226f9bddc
[RLlib] Report timesteps_this_iter to Tune, so it can track/checkpoint/restore total timesteps trained. (#19264)
|
3 年之前 |
Sven Mika
|
ed85f59194
[RLlib] Unify all RLlib Trainer.train() -> results[info][learner][policy ID][learner_stats] and add structure tests. (#18879)
|
3 年之前 |
Sven Mika
|
c3a15ecc0f
[RLlib] Issue #13802: Enhance metrics for `multiagent->count_steps_by=agent_steps` setting. (#14033)
|
3 年之前 |
Michael Luo
|
a2d1215200
[RLlib] Execution Annotation (#13036)
|
3 年之前 |
Edward Oakes
|
cde711aaf1
Revert "[RLLib] Execution-Folder Type Annotations (#12760)" (#12886)
|
3 年之前 |
Michael Luo
|
becca1424d
[RLLib] Execution-Folder Type Annotations (#12760)
|
3 年之前 |
Sven Mika
|
b0b0463161
[RLlib] Trajectory View API (preparatory cleanup and enhancements). (#9678)
|
4 年之前 |
Eric Liang
|
1e0e1a45e6
[rllib] Add type annotations for evaluation/, env/ packages (#9003)
|
4 年之前 |
Eric Liang
|
9f04a65922
[rllib] Add PPO+DQN two trainer multiagent workflow example (#8334)
|
4 年之前 |
Eric Liang
|
baadbdf8d4
[rllib] Execute PPO using training workflow (#8206)
|
4 年之前 |
Eric Liang
|
31b40b00f6
[rllib] Pull out experimental dsl into rllib.execution module, add initial unit tests (#7958)
|
4 年之前 |