Issues
- 0
Examples `online_q_learning` not working
#136 opened by marcdelabarrera - 0
- 6
Stop action gradient in policy gradient loss
#109 opened by danijar - 1
Writing a MPO example (help I'm confused)
#118 opened by act65 - 2
Relax numpy version requirement
#110 opened by wookayin - 1
PopArt example bug
#111 opened by kinalmehta - 0
- 2
- 0
Latest release of rlax (0.1.2) is incompatible with the latest release of jax (0.3.16)
#97 opened by hr0nix - 1
Title mistake in docs
#89 opened by HenriDeh - 2
Question of `logprob_fn` in the `squashed_gaussian`?
#54 opened by fuyw - 0
Make documentation download-able as PDF?
#64 opened by IanQS - 0
Support for Bandits?
#62 opened by IanQS - 1
- 1
Implementation for Squashed Gaussian
#11 opened by jy-cds - 4
Need of central documentation
#37 opened by EngineerKhan - 0
- 1
- 1
- 2
vtrace uses `lax.scan`?
#16 opened by thisiscam - 0
rlax is broken on Python 3.9
#13 opened by dionhaefner - 7
Install error with jaxlib version 0.1.47
#7 opened by renos - 7
Questions re: RLax Value Learning ?
#9 opened by RylanSchaeffer - 1
missing library: `import optax`
#8 opened by jharmsen - 11
Documentation and Examples
#5 opened by joaogui1 - 1
can not find setup.py for pip install
#2 opened by chris-chris