Codes
Register Sign In
English
English 简体中文
openoker
/
ray
1
0
Fork 0
Files Issues 0 Wiki
Branch: ubranch-1
Branches Tags

Commit History

Author SHA1 Message Date
  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

Newer Older