-
The current implementation of `policy_gradient_loss` is:
```python
log_pi_a_t = distributions.softmax().logprob(a_t, logits_t)
adv_t = jax.lax.select(use_stop_gradient, jax.lax.stop_gradient(adv_t)…
-
(Updated for clarity)
Apologies if I'm wrong, but it seems to me that there are some mathematical issues in [unit 4 "diving deeper..."](https://github.com/huggingface/deep-rl-class/blob/main/units/en…
-
# Pierre-Luc Bacon
The project description suggests that RLPy is mainly about value function based algorithms. However, I think it'd be nice to add Will Dabney's implementation of some of the popular…
-
WARNING: Logging before InitGoogleLogging() is written to STDERR
I1022 16:02:46.179663 104725 init.cc:47] Init commandline: dummy run.py --tryfromenv=use_pinned_memory,check_nan_inf,benchmark,warpctc…
-
Thank you for your great work!
I refactored the code [repo is here](https://github.com/baichen99/Finite-expression-method/blob/main/train_fex_possion.py), but it seems that the use of policy gradie…
-
http://proceedings.mlr.press/v32/silver14.pdf
-
https://scholar.google.com/scholar?hl=ja&as_sdt=0%2C5&q=Deterministic+Policy+Gradient+Algorithms&btnG=
-
-
-
Hi @yanji84,
first of all compliments on your code, the clear structure makes it easy to understand. However, I think there are two issues with how you compute the policy gradients in the `backward…