polixir/NeoRL

Issues

• Update Aim version and add Aim running instructions on README

  #7 opened 9 months ago by SGevorg
  1

• Learning curves in IB

  #9 opened 9 months ago by joseluperez1999
  1

• Action space difference between datasset and environment

  #8 opened 9 months ago by mrqy0610
  2

• Question regarding the reward of sales promotion training dataset

  #10 opened 9 months ago by britisony
  3

• Expert scores & random scores for normalization

  #11 opened 9 months ago by kwanyoungpark
  2

• Unable to reproduce results for BCQ

  #6 opened 3 years ago by Astro-Eric
  0

• Baseline Policies and Raw Results

  #2 opened 3 years ago by vkurenkov
  2

• Next_Observation and Reward clamping in MOPO

  #5 opened 3 years ago by ssimonc
  2

• Can I use NeoRL, to generate a dataset, in the d4rl format, e.g for the finance environment?

  #4 opened 3 years ago by krish240574
  2

• LSTM

  #3 opened 3 years ago by yosoul93
  1

• Question regarding the dynamics pre-training

  #1 opened 3 years ago by ssimonc
  2