Commit History

Author SHA1 Message Date
  Sven Mika 9a8ca6a69d [RLlib] Fix Atari learning test regressions (2 bugs) and 1 minor attention net bug. (#18306) 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 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 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 8726521604 [RLlib] JAXPolicy prep PR #2 (move get_activation_fn (backward-compatibly), minor fixes and preparations). (#13091) 3 years ago
  Michael Luo 59ccbc0fc7 [RLlib] Model Annotations: Tensorflow (#11964) 4 years ago
  Sven Mika 957877ad3f Tf version of VisionNet (ray/rllib/model/tf/vision_net.py) crashes iff len(conv-filters)=1. (#11330) 4 years ago
  Sven Mika 28ab797cf5 [RLlib] Deprecate old classes, methods, functions, config keys (in prep for RLlib 1.0). (#10544) 4 years ago
  Barak Michener 8e76796fd0 ci: Redo `format.sh --all` script & backfill lint fixes (#9956) 4 years ago
  Sven Mika 5d5643e633 [RLlib] Add informative error message when bad Conv2D stack is used with fixed `num_outputs` (no flattening at end). (#9966) 4 years ago
  Sven Mika 43043ee4d5 [RLlib] Tf2x preparation; part 2 (upgrading `try_import_tf()`). (#9136) 4 years ago
  Sven Mika 2589309cf0 [RLlib] Make sure torch and tf behave the same wrt conv2d nets. (#8785) 4 years ago
  Sven Mika 796a834c48 [RLlib] Attention Net integration into ModelV2 and learning RL example. (#8371) 4 years ago