Sven Mika
|
9e6b871739
[RLlib] Better utils for flattening complex inputs and enable prev-actions for LSTM/attention for complex action spaces. (#21330)
|
2 年之前 |
Sven Mika
|
f3397b6f48
[RLlib] Minor fixes/cleanups; chop_into_sequences now handles nested data. (#19408)
|
3 年之前 |
Avnish Narayan
|
026bf01071
[RLlib] Upgrade gym version to 0.21 and deprecate pendulum-v0. (#19535)
|
3 年之前 |
Sven Mika
|
2d24ef0d32
[RLlib] Add all simple learning tests as `framework=tf2`. (#19273)
|
3 年之前 |
Sven Mika
|
0b308719f8
[RLlib; Docs overhaul] Docstring cleanup: rllib/utils (#19829)
|
3 年之前 |
Sven Mika
|
d0014cd351
[RLlib] Policies get/set_state fixes and enhancements. (#16354)
|
3 年之前 |
Michael Luo
|
4cbe13cdfd
[RLlib] CQL loss fn fixes, MuJoCo + Pendulum benchmarks, offline-RL example script w/ json file. (#15603)
|
3 年之前 |
Sven Mika
|
cecfc3b43b
[RLlib] Multi-GPU support for Torch algorithms. (#14709)
|
3 年之前 |
Sven Mika
|
592c161032
[RLlib] Issue 12118: LSTM prev-a/r should be separately configurable. Fix missing prev-a one-hot encoding. (#12397)
|
3 年之前 |
Sven Mika
|
03ab86567f
[RLlib] Layout of Trajectory View API (new class: Trajectory; not used yet). (#9269)
|
4 年之前 |
Sven Mika
|
43043ee4d5
[RLlib] Tf2x preparation; part 2 (upgrading `try_import_tf()`). (#9136)
|
4 年之前 |
Sven Mika
|
7ec2223c84
[RLlib] DDPG PyTorch actor-model was missing sigmoid layer (#8188)
|
4 年之前 |
Sven Mika
|
428516056a
[RLlib] SAC Torch (incl. Atari learning) (#7984)
|
4 年之前 |
Sven Mika
|
22ccc43670
[RLlib] DQN torch version. (#7597)
|
4 年之前 |
Sven Mika
|
1d4823c0ec
[RLlib] Add testing framework_iterator. (#7852)
|
4 年之前 |
Sven Mika
|
5537fe13b0
[RLlib] Exploration API: ParamNoise Integration into DQN; working example/test cases. (#7814)
|
4 年之前 |
Sven Mika
|
66df8b8c35
[RLlib] Working/learning example: PPO + torch + LSTM. (#7797)
|
4 年之前 |
Sven Mika
|
0db2046b0a
[RLlib] Policy.compute_log_likelihoods() and SAC refactor. (issue #7107) (#7124)
|
4 年之前 |
Sven
|
60d4d5e1aa
Remove future imports (#6724)
|
4 年之前 |
Sven
|
8b16847c02
Get utils ready for better Agent torch support. (#6561)
|
4 年之前 |