facebookresearch/Pearl

Issues

• PPO on continuous actions

  #77 opened 6 months ago by zaksemenov
  7

• How exactly is Pearl "Production-ready"?

  #100 opened a month ago by ogencoglu
  1

• Add voice message capabilities

  #99 opened 2 months ago by Yashkumar888
  1

• Rainbow DQN

  #98 opened 2 months ago by brianferrell787
  1

• RuntimeError for action shape

  #91 opened 4 months ago by lz1159435992
  3

• What is the use of the attribute 'state' in the RecEnv from the single item recommender tutorial?

  #97 opened 3 months ago by davera-017
  1

• Pip availability and clear versioning in branches/tags/releases

  #76 opened 6 months ago by cryptexis
  2

• cuda out of meomory

  #72 opened 5 months ago by lz1159435992
  16

• Support for imitation learning

  #90 opened 4 months ago by e-zorzi
  3

• NotImplementedError: The Gym space 'Tuple' is not yet supported in Pearl.

  #54 opened 8 months ago by EduardoGarrido90
  2

• save the trained agent for reuse

  #74 opened 6 months ago by lz1159435992
  2

• Bug in tutorial single item recommender system: can't instantiate abstract class RecEnv

  #87 opened 5 months ago by milmin
  3

• Error when running the Single Item Recommender System Notebook

  #79 opened 5 months ago by davera-017
  5

• Simplify actor-critic with shared layers

  #73 opened 7 months ago by panoskyriakis
  2

• Creating a project roadmap

  #81 opened 6 months ago by aleksa-sukovic
  1

• How is Pearl different from TorchRL?

  #80 opened 6 months ago by listener17
  1

• TorchRL Vs Pearl: What's the difference & when to use one?

  #78 opened 6 months ago by deependujha
  1

• custom network issue

  #75 opened 6 months ago by jyan-R
  1

• Functionality for Stein variational policy gradient and/or regularization through the use of prior policies

  #44 opened 8 months ago by leonhalgryn
  2

• Is there some limitation with the dimensions of actions and observations?

  #27 opened 9 months ago by paapu88
  5

• Question: train_via_uniform_data

  #65 opened 7 months ago by cryptexis
  10

• More tutorials are needed

  #33 opened 9 months ago by codeman6688
  5

• Unable to export loss values from TD3

  #69 opened 7 months ago by zchiam002
  12

• Model Export

  #45 opened 8 months ago by wglassly
  5

• Frozen lake

  #59 opened 8 months ago by mehrdad78
  5

• Frozen-lake tutorial

  #64 opened 7 months ago by mehrdad78
  1

• What is the policy of Pull Requests ?

  #62 opened 7 months ago by cryptexis
  3

• Issues when trying to use torch.jit.script()

  #58 opened 8 months ago by ValerieF412
  2

• Use pearl with custom pytorch model

  #60 opened 8 months ago by BoccheseGiacomo
  6

• Does Pearl support serving in TorchScript?

  #56 opened 8 months ago by ValerieF412
  1

• LSTM History Summarization Poor Performance

  #47 opened 8 months ago by GreatArcStudios
  8

• PPO + LSTM issues

  #29 opened 8 months ago by antoine-galataud
  3

• STAC algorithm

  #37 opened 9 months ago by EloyAnguiano
  1

• Will n-D observation states be supported?

  #39 opened 9 months ago by GreatArcStudios
  1

• Custom space vectorizers

  #36 opened 9 months ago by EloyAnguiano
  1

• Mixed Discrete + Continuous Action Spaces

  #22 opened 8 months ago by kuza55
  6

• MultiDiscrete Action space not support

  #24 opened 8 months ago by zuoningz
  1

• online_learning function meet custom gym env without register

  #42 opened 8 months ago by jzxhi31
  1

• FIFO On-Policy replay buffers lead to error with PPO

  #40 opened 8 months ago by GreatArcStudios
  2

• REINFORCE actor update missing discount factor

  #46 opened 8 months ago by GreatArcStudios
  2

• Hidden dim of LSTM history summarization module must be equal to observation dim

  #31 opened 8 months ago by antoine-galataud
  2

• Recommender System Example

  #35 opened 8 months ago by mehrdad78
  1

• How to infer result of the tutorials?

  #41 opened 8 months ago by Souptik-lilly
  1

• Demo DQN-LSTM dose not converge

  #34 opened 9 months ago by JunYao0619
  3

• Multi-agent Reinforcement Learning?

  #28 opened 9 months ago by paapu88
  1

• Typo in the docs

  #21 opened 9 months ago by Vamsi995
  1

• Graph Neural Network Compatibility

  #20 opened 9 months ago by rami1232
  1

• FAlcon

  #16 opened 9 months ago by arita37
  1

• Gymnasium?

  #19 opened 9 months ago by drozzy
  1

• PolicyLearner batch_size versus episode_steps clarification

  #15 opened 9 months ago by GreatArcStudios
  4