Commits

Breadcrumbs

History for

onmaster

User selector

All users

Datepicker

All time

Commit History

Commits on Mar 31, 2023

• [RLlib] DreamerV3: Episode-based replay buffer implementation. (ray-project#33801)

  sven1977

  authored
  31f5f5b

  Copy full SHA for 31f5f5b

• [RLlib] DM control suite wrapper fix: dtype of obs needs to be pinned to float32. (ray-project#33876)

  sven1977

  authored
  8f3ee83

  Copy full SHA for 8f3ee83

Commits on Mar 30, 2023

• [RLlin] Add dist_inputs to action sampler fn returns in TorchPolicyV2 (ray-project#33795)

  Show description for bf02571
  ArturNiederfahrenhorst

  authored
  bf02571

  Copy full SHA for bf02571

Commits on Mar 29, 2023

• [RLlib] Remove is_distributed() and make_distributed() functions for Learner API (ray-project#33781)

  avnishn

  authored
  1c2e8e2

  Copy full SHA for 1c2e8e2

• [RLlib] Don't serialize config in Policy states (unless needed for msgpack-type checkpoints). (ray-project#33865)

  sven1977

  authored
  a701fa1

  Copy full SHA for a701fa1

• [RLlib] Fix MultiCallbacks class: To be used only with utility function that returns a class to use in the config. (ray-project#33863)

  sven1977

  authored
  ef31bc6

  Copy full SHA for ef31bc6

Commits on Mar 28, 2023

• [RLlib] Fix APEX-DQN deprecated add_batch call (replace with add). (ray-project#33814)

  avnishn

  authored
  d418fa7

  Copy full SHA for d418fa7

• [RLlib] AlgorithmConfig.update_from_dict needs to work for MultiCallbacks. (ray-project#33796)

  Show description for bb1909c
  

  Jun Gong

  and

  sven1977

  authored
  bb1909c

  Copy full SHA for bb1909c

• [RLlib][RLModule] Fixed the learning test regression introduced via learner_api in pendulum (ray-project#33778)

  Show description for 50d7852
  kouroshHakha

  authored
  50d7852

  Copy full SHA for 50d7852

• [RLlib] Add free floating logstd to RL Modules/Catalog (ray-project#33673)

  Show description for b5312d1
  ArturNiederfahrenhorst

  authored
  b5312d1

  Copy full SHA for b5312d1

• [RLlib][RLModule] Disable RLModule in test_ppo.py since the test is overly designed with ModelV2 stack in mind. Also the schedulers for entropy coeff / learning rate are not supported in the learne…

  Show description for bbc6d3c
  kouroshHakha

  authored
  bbc6d3c

  Copy full SHA for bbc6d3c

• [RLlib]Fix categorical nested inside multi distribution (ray-project#33768)

  Show description for 5f50e5b
  ArturNiederfahrenhorst

  authored
  5f50e5b

  Copy full SHA for 5f50e5b

Commits on Mar 27, 2023

• [RLlib] Fix: Recovered eval worker should use eval-config's policy_mapping_fn and policy_to_train fn, not the main train workers' ones. (ray-project#33648)

  Show description for d127273
  sven1977

  authored
  d127273

  Copy full SHA for d127273

• [RLlib][RLModule] Use forward_exploration() inside the unit-test for test_log_likelihood since the action_logps are not necessary fields for exploration (ray-project#33745)

  Show description for 4b0ded2
  kouroshHakha

  authored
  4b0ded2

  Copy full SHA for 4b0ded2

• [RLlib][RLModule] Disabled RLModule API on cartpole_ppo_fake_gpu tests becauase of LSTMs (ray-project#33728)

  Show description for 7dac365
  kouroshHakha

  authored
  7dac365

  Copy full SHA for 7dac365

• [RLlib][RLModule] Disabled RLModule in Two trainer workflow example (ray-project#33727)

  Show description for ba04d01
  kouroshHakha

  authored
  ba04d01

  Copy full SHA for ba04d01

• [RLlib][RLModule] Disabled rl_module in one of the subtests in test_curiosity (ray-project#33726)

  Show description for 14c1595
  kouroshHakha

  authored
  14c1595

  Copy full SHA for 14c1595

• [RLlib] Fixed a typo in multi-agent definition using RLModules in test_env_runner_v2::test_guess_the_number_multi_agent (ray-project#33723)

  Show description for b1174d2
  kouroshHakha

  authored
  b1174d2

  Copy full SHA for b1174d2

Commits on Mar 26, 2023

• [RLlib] APPO TF with RLModule and Learner API (ray-project#33310)

  Show description for 10d12f8
  avnishn

  authored
  10d12f8

  Copy full SHA for 10d12f8

• [RLlib] fix preprocessor test (ray-project#33719)

  Show description for 427ac2c
  ArturNiederfahrenhorst

  authored
  427ac2c

  Copy full SHA for 427ac2c

Commits on Mar 25, 2023

• [RLlib] Introduce preprocessors to RLModules/Catalog (ray-project#33447)

  Show description for deba909
  ArturNiederfahrenhorst

  authored
  deba909

  Copy full SHA for deba909

• [RLlib][RLModule][build_base] Disabling RLModule API for LSTM / Attn (ray-project#33662)

  Show description for 9a2d5f4
  kouroshHakha

  authored
  9a2d5f4

  Copy full SHA for 9a2d5f4

Commits on Mar 24, 2023

• [RLlib][RLModule][build_base] Disabled Centralized Critic and Curiosity tests with RLModules (ray-project#33663)

  Show description for 17596b0
  kouroshHakha

  authored
  17596b0

  Copy full SHA for 17596b0

• [RLlib][Data][build_base] Fix RLlib test build rules that should trigger when there are dataset changes. (ray-project#33683)

  Show description for 8b1c702
  kouroshHakha

  authored
  8b1c702

  Copy full SHA for 8b1c702

• [RLlib] Add support for MultiCategorical and MultiActionDistribution for RL Modules (ray-project#32938)

  Show description for 5f40e22
  ArturNiederfahrenhorst

  authored
  5f40e22

  Copy full SHA for 5f40e22

• [RLlib] Change default framework from tf to torch (ray-project#33604)

  Show description for 8d2dc9a
  kouroshHakha

  authored
  8d2dc9a

  Copy full SHA for 8d2dc9a

• [RLlib][RLModule] Fixed a bug where on the new RLModule API we could not rollout (ray-project#33331)

  Show description for 70c4d5c
  kouroshHakha

  authored
  70c4d5c

  Copy full SHA for 70c4d5c

• [RLlib] Remove a warning for users that they are using the old gym API. (ray-project#33587)

  ArturNiederfahrenhorst

  authored
  c1e92d7

  Copy full SHA for c1e92d7

• [RLlib] Change scope of PPO tests to comply with currently supported set of spaces in RLModules for PPO. (ray-project#32940)

  ArturNiederfahrenhorst

  authored
  b671bc0

  Copy full SHA for b671bc0

Commits on Mar 23, 2023

• [RLlib] Implement Impala Torch in RLModule / Learner stack. (ray-project#33271)

  ArturNiederfahrenhorst

  authored
  f4a2044

  Copy full SHA for f4a2044

• [RLlib] Make it so that the learner update allows for multiple SGD updates always. (ray-project#33471)

  avnishn

  authored
  0695863

  Copy full SHA for 0695863

• [RLlib][CI] Tag those RLlib tests that needs to be tiggered upon Ray data changes (ray-project#33488)

  Show description for dee4e2e
  kouroshHakha

  authored
  dee4e2e

  Copy full SHA for dee4e2e

Commits on Mar 22, 2023

• [RLlib] Checkpoints are convertible to msgpack-based checkpoints (to make them python-version-independent). (ray-project#32779)

  sven1977

  authored
  2e6de87

  Copy full SHA for 2e6de87

• [RLlib][Docs] Restructure Utils API page (ray-project#33358)

  Show description for 61ae049
  kouroshHakha

  authored
  61ae049

  Copy full SHA for 61ae049

Commits on Mar 21, 2023

• [RLlib][Docs] Restructure RLModule API page (ray-project#33363)

  Show description for 74af29a
  kouroshHakha

  authored
  74af29a

  Copy full SHA for 74af29a

Pagination

Previous

Next