Commits

Breadcrumbs

History for

onfa16c76

User selector

All users

Datepicker

All time

Commit History

Commits on Jun 16, 2020

• [RLlib] Prototype of a DynaTrainer (for env dynamics learning in upcoming MBMPO algo). (ray-project#8860)

  sven1977

  authored
  14405b9

  Copy full SHA for 14405b9

• [RLlib] Minor rllib.utils cleanup. (ray-project#8932)

  sven1977

  authored
  7008902

  Copy full SHA for 7008902

• Issue 8919 checkpoint at end ignored (ray-project#8933)

  sven1977

  authored
  0c7764b

  Copy full SHA for 0c7764b

• [RLlib] Issue 8714: QMIX init error w/ tuple obs space. (ray-project#8936)

  sven1977

  authored
  bdf1404

  Copy full SHA for bdf1404

Commits on Jun 13, 2020

• [RLlib] Add testing Policy.compute_single_action() for all agents. (ray-project#8903)

  sven1977

  authored
  4ed796a

  Copy full SHA for 4ed796a

• [rllib] Flexible multi-agent replay modes and replay_sequence_length (ray-project#8893)

  ericl

  authored
  34bae27

  Copy full SHA for 34bae27

Commits on Jun 11, 2020

• [RLlib] Issue 8889: action clipping bug ppo not learning mujoco (ray-project#8898)

  sven1977

  authored
  8d1ccfd

  Copy full SHA for 8d1ccfd

• [RLlib] Unity3d soccer benchmarks (ray-project#8834)

  sven1977

  authored
  a90cd0f

  Copy full SHA for a90cd0f

• [RLlib] use Mapping instead of dict in summarize() to accommodate non-dict grads/params (e.g. haiku's frozendict) (ray-project#8793)

  KristianHolsheimer

  authored
  ea965d7

  Copy full SHA for ea965d7

• Fix typo in docs for LinearDiscreteEnv (ray-project#8891)

  deanwampler

  authored
  53712d2

  Copy full SHA for 53712d2

Commits on Jun 10, 2020

• [Testing] Fix LINT/sphinx errors. (ray-project#8874)

  sven1977

  authored
  0ba7472

  Copy full SHA for 0ba7472

Commits on Jun 9, 2020

• [rllib] Set framework to tf by default and remove import checks; "Auto" option (ray-project#8748)

  Show description for 831b2fe
  

  ericl

  and

  sven1977

  authored
  831b2fe

  Copy full SHA for 831b2fe

• Change os.uname()[1] and socket.gethostname() to the portable and faster platform.node_ip() (ray-project#8839)

  Show description for f93bb00
  

  mehrdadn

  and

  web-flow

  authored
  f93bb00

  Copy full SHA for f93bb00

Commits on Jun 6, 2020

• Bug fix in the contextual bandit's linear_regression.py model. (ray-project#8815)

  sven1977

  authored
  ad695a8

  Copy full SHA for ad695a8

• [rllib] Support for complex / variable-length observation spaces (ray-project#8393)

  ericl

  authored
  be26a7b

  Copy full SHA for be26a7b

Commits on Jun 5, 2020

• [RLlib] Issue 8412 (Adam vars not stored in ModelV2). (ray-project#8480)

  sven1977

  authored
  25c0974

  Copy full SHA for 25c0974

• [RLlib] Fix use_lstm flag for ModelV2 (w/o ModelV1 wrapping) and add it for PyTorch. (ray-project#8734)

  sven1977

  authored
  c74dc58

  Copy full SHA for c74dc58

• [RLlib] Issue 8769 broken OOM tests_dir cases (R & S). (ray-project#8770)

  sven1977

  authored
  97d524c

  Copy full SHA for 97d524c

Commits on Jun 4, 2020

• [RLlib] Sample batch docs and cleanup. (ray-project#8778)

  sven1977

  authored
  368088b

  Copy full SHA for 368088b

• Fix dict/tuple hybrid action space for tensorflow eager execution (ray-project#8781)

  Coac

  authored
  aee0113

  Copy full SHA for aee0113

Commits on Jun 3, 2020

• [rllib] Add type annotations to Trainer class (ray-project#8642)

  Show description for 1e4a136
  ericl

  authored
  1e4a136

  Copy full SHA for 1e4a136

• [RLlib] Bug fixes and tests in DiagGaussian (ray-project#8676)

  09wakharet

  authored
  c773824

  Copy full SHA for c773824

• [RLlib] Make envs specifiable in configs by their class path. (ray-project#8750)

  sven1977

  authored
  b37a162

  Copy full SHA for b37a162

Commits on Jun 2, 2020

• Remove accidental passes in rllib, tune (ray-project#8742)

  edoakes

  authored
  ae312af

  Copy full SHA for ae312af

Commits on May 30, 2020

• [RLlib] Unity3D integration (n Unity3D clients vs learning server). (ray-project#8590)

  sven1977

  authored
  d8a081a

  Copy full SHA for d8a081a

Commits on May 29, 2020

• [RLlib] Fix broken tune tests in master due to framework=auto errors. (ray-project#8672)

  sven1977

  authored
  d483ed2

  Copy full SHA for d483ed2

Commits on May 28, 2020

• [rllib] Do not store torch tensors when using grad clipping (ray-project#8509)

  iamhatesz

  authored
  f266318

  Copy full SHA for f266318

Commits on May 27, 2020

• [RLlib] Auto-framework, retire use_pytorch in favor of framework=... (ray-project#8520)

  sven1977

  authored
  2746fc0

  Copy full SHA for 2746fc0

• fixing polynomial schedule horizon (ray-project#7795)

  

  konichuvak

  authored
  13c2e13

  Copy full SHA for 13c2e13

• resolved NameError in ray.tune() call (ray-project#8494)

  ceteri

  authored
  067bbb6

  Copy full SHA for 067bbb6

• [RLlib] Removed config["sample_async"] restriction for A3C-torch. (ray-project#8617)

  sven1977

  authored
  c7a2e3f

  Copy full SHA for c7a2e3f

• [RLlib] utils/spaces ... (ray-project#8608)

  sven1977

  authored
  6d19619

  Copy full SHA for 6d19619

• [RLlib] Add 2 Transformer learning test cases on StatelessCartPole (PPO and IMPALA). (ray-project#8624)

  sven1977

  authored
  0422e9c

  Copy full SHA for 0422e9c

Commits on May 26, 2020

• [RLlib] Benchmark and regression test yaml cleanup and restructuring. (ray-project#8414)

  sven1977

  authored
  baa0534

  Copy full SHA for baa0534

Commits on May 23, 2020

• Fix missing learning rate and entropy coeff schedule for torch PPO (ray-project#8572)

  janblumenkamp

  authored
  d6f78f5

  Copy full SHA for d6f78f5

Pagination

Previous

Next