Commits

Branch selector

 master

User selector

simonsays1980

Datepicker

All time

Commit History

Commits on May 3, 2024

• [RLlib] - Fix APPO RLModule inference-only problems. (ray-project#45111)

  simonsays1980

  authored
  45d5640

  Copy full SHA for 45d5640

Commits on May 2, 2024

• [RLlib] Fix numerical overflow in global_norm and norm gradient clipping in case of (many) large gradient matrices. (ray-project#45055)

  simonsays1980

  authored
  711f386

  Copy full SHA for 711f386

• [RLlib] - Adding missing __init__.py in 'algorithms/sac/torch' that was throwing an error. (ray-project#45070)

  simonsays1980

  authored
  0e5cfaf

  Copy full SHA for 0e5cfaf

Commits on Apr 30, 2024

• [RLlib] Fix bad assertion error in PPO when use_kl_loss=False. (ray-project#45031)

  simonsays1980

  authored
  89a6393

  Copy full SHA for 89a6393

• [RLlib] - Get and set states in MultiAgentEpisode and SingleAgentEpisode. (ray-project#45012)

  simonsays1980

  authored
  a45bfe3

  Copy full SHA for a45bfe3

Commits on Apr 29, 2024

• [RLlib] Fix CI test: examples/checkpoints/checkpoint_by_custom_criteria.py. (ray-project#45030)

  simonsays1980

  authored
  0b34086

  Copy full SHA for 0b34086

Commits on Apr 25, 2024

• [RLlib] Implementation of MultiAgentEpisodeReplayBuffer for the new API stack. (ray-project#44450)

  simonsays1980

  authored
  97e910b

  Copy full SHA for 97e910b

Commits on Apr 23, 2024

• [RLlib] "Light-weighted" RLModules for use in inference-only or exploration-only settings. (ray-project#44797)

  simonsays1980

  authored
  bf39be7

  Copy full SHA for bf39be7

Commits on Apr 22, 2024

• [RLlib] Bug fix: 'train_batch_size_per_learner' could not be used in dependent Tune search space. (ray-project#44868)

  simonsays1980

  authored
  2f7b0d9

  Copy full SHA for 2f7b0d9

Commits on Apr 17, 2024

• [RLlib, Tune, AIR] Support of images and video logging in wandb. (ray-project#43356)

  simonsays1980

  authored
  dcc3847

  Copy full SHA for dcc3847

Commits on Apr 16, 2024

• [RLlib] Add example: Pre-train an RLModule single-agent, then bring checkpoint into multi-agent setup and continue training. (ray-project#44674)

  simonsays1980

  authored
  d8c7234

  Copy full SHA for d8c7234

Commits on Apr 15, 2024

• [RLlib] Better support and separation-of-concerns for model_config_dict in new API stack. (ray-project#44263)

  simonsays1980

  authored
  9cb1dc9

  Copy full SHA for 9cb1dc9

Commits on Apr 11, 2024

• [RLlib] Added benchmark experiment for SAC with MuJoCo, PPO with MuJoCo and DQN with Atari. (ray-project#44262)

  simonsays1980

  authored
  61ef56f

  Copy full SHA for 61ef56f

Commits on Apr 2, 2024

• [RLlib] Add warnings to 'sychronous_parallel_sample' in case no sample data collected. (ray-project#44340)

  simonsays1980

  authored
  fb89bf8

  Copy full SHA for fb89bf8

Commits on Mar 22, 2024

• [RLlib] DQN Rainbow on new API stack (w/ EnvRunner):training_step implementation. (ray-project#43198)

  simonsays1980

  authored
  9907a28

  Copy full SHA for 9907a28

Commits on Mar 19, 2024

• [RLlib] Removes device info from RLModule state (e.g. when creating checkpoints). (ray-project#43906)

  simonsays1980

  authored
  94fd80f

  Copy full SHA for 94fd80f

Commits on Mar 18, 2024

• [RLlib] Added a hot fix to avoid a spec checker error in 'PPOTorchRLModule._compute_values' when using a non-shared stateful encoder. In addition fixed an error that occurs while slicing batches wi…

  Show description for fd0c148
  simonsays1980

  authored
  fd0c148

  Copy full SHA for fd0c148

Commits on Mar 11, 2024

• [RLlib] Added funcitonality to add infos and extra_model_outputs to the sample output of PrioritizedEpisodeReplayBuffer. (ray-project#43496)

  simonsays1980

  authored
  ec68337

  Copy full SHA for ec68337

Commits on Mar 6, 2024

• [RLlib] Docs and test code for PrioritizedEpisodeReplayBuffer. (ray-project#43458)

  simonsays1980

  authored
  87ec8f6

  Copy full SHA for 87ec8f6

Commits on Feb 29, 2024

• [RLlib] Functionality for SingleAgentEpisode and MultiAgentEpisode in synchronous_parallel_sample. (ray-project#43275)

  simonsays1980

  authored
  a54f0fc

  Copy full SHA for a54f0fc

Commits on Feb 28, 2024

• [RLlib] DQN Rainbow on new API stack: RLModule and Catalog together with TorchNoisyMLP. (ray-project#43199)

  simonsays1980

  authored
  73a5264

  Copy full SHA for 73a5264

Commits on Feb 27, 2024

• [RLlib] DQN Rainbow Learner with new API stack (and EnvRunner API). (ray-project#43196)

  simonsays1980

  authored
  359edb9

  Copy full SHA for 359edb9

Commits on Feb 22, 2024

• [RLlib] Enable custom async evaluation function on the new API stack (w/ EnvRunner). (ray-project#43084)

  simonsays1980

  authored
  fa99314

  Copy full SHA for fa99314

Commits on Feb 21, 2024

• [RLlib] Uniform random n-step sampling in PrioritizedEpisodeReplayBuffer. (ray-project#43258)

  simonsays1980

  authored
  73293e2

  Copy full SHA for 73293e2

Commits on Feb 20, 2024

• [RLlib, Tune] TBXLogger: Add images. (ray-project#37822)

  simonsays1980

  authored
  60fc906

  Copy full SHA for 60fc906

Commits on Feb 9, 2024

• [RLlib] SAC on new API stack (w/ EnvRunner and ConnectorV2): training_step() method added to SACAlgorithm. (ray-project#42571)

  simonsays1980

  authored
  ee87ece

  Copy full SHA for ee87ece

Commits on Feb 1, 2024

• [RLlib] Prioritized version of an episode-based replay buffer. (ray-project#42832)

  simonsays1980

  authored
  d8d775f

  Copy full SHA for d8d775f

• [RLlib] Implement MultiAgentEnvRunner class. (ray-project#41558)

  simonsays1980

  authored
  3dea811

  Copy full SHA for 3dea811

Commits on Jan 25, 2024

• [RLlib] SAC on new API stack (w/ EnvRunner and ConnectorV2): SACLearner and SACTorchLearner classes. (ray-project#42570)

  simonsays1980

  authored
  622f4d3

  Copy full SHA for 622f4d3

Commits on Jan 24, 2024

• [RLlib] SAC on new API stack: SACRLModule and SACTorchRLModule. (ray-project#42568)

  simonsays1980

  authored
  93ee64c

  Copy full SHA for 93ee64c

• [RLlib] Issue 41370: Tune update_config should use config.to_dict() if config is an _Config. (ray-project#42116)

  simonsays1980

  authored
  1826060

  Copy full SHA for 1826060

Commits on Jan 10, 2024

• [RLlib] Add functionality to define kernel and bias initializers for RLModules. (ray-project#42137)

  simonsays1980

  authored
  1aec3f1

  Copy full SHA for 1aec3f1

Commits on Jan 4, 2024

• [RLlib] Cast types for new configurations in PB2. (ray-project#42181)

  simonsays1980

  authored
  2b57ee9

  Copy full SHA for 2b57ee9

• [RLlib] Fix issue 40910 gymnasium docs. (ray-project#42117)

  simonsays1980

  authored
  952cc77

  Copy full SHA for 952cc77

Commits on Jan 2, 2024

• [RLlib] Issue 40347: Fix saving and loading algos by loading stored learner state. (ray-project#42090)

  simonsays1980

  authored
  61b531c

  Copy full SHA for 61b531c

Pagination

Previous

Next