Avnish Narayan
|
026bf01071
[RLlib] Upgrade gym version to 0.21 and deprecate pendulum-v0. (#19535)
|
3 years ago |
Sven Mika
|
0b308719f8
[RLlib; Docs overhaul] Docstring cleanup: rllib/utils (#19829)
|
3 years ago |
Sven Mika
|
61a1274619
[RLlib] No Preprocessors (part 2). (#18468)
|
3 years ago |
Sven Mika
|
8a066474d4
[RLlib] No Preprocessors; preparatory PR #1 (#18367)
|
3 years ago |
Sven Mika
|
9a8ca6a69d
[RLlib] Fix Atari learning test regressions (2 bugs) and 1 minor attention net bug. (#18306)
|
3 years ago |
Francesco Stranieri
|
01c533c171
[rlib] Independent bound for each dimension AssertionError #16845 (#16860)
|
3 years ago |
Gerges Dib
|
f8cf4a1985
[RLlib] Fixed import tensorflow when module not available (#16171)
|
3 years ago |
Sven Mika
|
e973b726c2
[RLlib] Support native tf.keras.Models (part 2) - Default keras models for Vision/RNN/Attention. (#15273)
|
3 years ago |
Sven Mika
|
bb8a286cbc
[RLlib] Support native tf.keras.Model (milestone toward obsoleting ModelV2 class). (#14684)
|
3 years ago |
Sven Mika
|
cecfc3b43b
[RLlib] Multi-GPU support for Torch algorithms. (#14709)
|
3 years ago |
Sven Mika
|
b267f1f1ba
[RLlib] Add support for Int-Box action spaces. (#15012)
|
3 years ago |
Sven Mika
|
04bc0a9828
[RLlib] Remove all non-trajectory view API code. (#14860)
|
3 years ago |
Sven Mika
|
e7557ae433
[RLlib] Issue 13132: DQN does not update target net after restore (#14838)
|
3 years ago |
Sven Mika
|
ee4b6e7e3b
[RLlib] Unity3D example broken due to change in ML-Agents API. Attention-net prev-n-a/r. Attention-wrapper works with images. (#14569)
|
3 years ago |
Sven Mika
|
52c94b7ee9
[RLlib] Allow SAC to use custom models as Q- or policy nets and deprecate "state-preprocessor" for image spaces. (#13522)
|
3 years ago |
Sven Mika
|
4bc257f4fb
[RLlib] Fix custom multi action distr (#13681)
|
3 years ago |
Jan Blumenkamp
|
964689b280
[RLlib] Fix bug in ModelCatalog when using custom action distribution (#12846)
|
3 years ago |
Sven Mika
|
56878221ed
[RLlib] Redo: Make TFModelV2 fully modular like TorchModelV2 (soft-deprecate register_variables, unify var names wrt torch). (#13363)
|
3 years ago |
Sven Mika
|
d49c3fae0b
[RLlib] Trajectory View API: Atari framestacking. (#13315)
|
3 years ago |
Kai Fricke
|
25f10a947a
Revert "[RLlib] Make TFModelV2 behave more like TorchModelV2: Obsolete register_variables. Unify variable dicts. (#13339)" (#13361)
|
3 years ago |
Sven Mika
|
e2b2abb88b
[RLlib] Make TFModelV2 behave more like TorchModelV2: Obsolete register_variables. Unify variable dicts. (#13339)
|
3 years ago |
Sven Mika
|
5d50d37f45
[RLlib] Issue 13330: No TF installed causes crash in `ModelCatalog.get_action_shape()` (#13332)
|
3 years ago |
Sven Mika
|
6f342a2221
[RLlib] Preparatory PR for: Documentation on Model Building. (#13260)
|
3 years ago |
Sven Mika
|
9eba1871bb
[RLlib] Support easy `use_attention=True` flag for using the GTrXL model. (#11698)
|
3 years ago |
Sven Mika
|
c524f86785
[RLlib] BC/MARWIL/recurrent nets minor cleanups and bug fixes. (#13064)
|
3 years ago |
Sven Mika
|
3f4bc16276
[RLlib] Add a minimal JAX ModelV2 (FCNet) to RLlib. (#12502)
|
3 years ago |
Sven Mika
|
592c161032
[RLlib] Issue 12118: LSTM prev-a/r should be separately configurable. Fix missing prev-a one-hot encoding. (#12397)
|
3 years ago |
Michael Luo
|
b2984d1c34
[RLlib] Model Annotations to Torch Models (#9749)
|
4 years ago |
Sven Mika
|
d9f1874e34
[RLlib] Minor fixes (torch GPU bugs + some cleanup). (#11609)
|
4 years ago |
Sven Mika
|
1ebcdf236f
[RLlib] Add support for custom MultiActionDistributions. (#11311)
|
4 years ago |