-
Hi Brainxyz, I am a PHd candidate/visiting scholar now majoring in Music technology in Georgia Tech. Your project inspires me a lot. It is very interesting to investigate GA in DRL. But I am new in th…
-
Are there any plans to add functionality to allow using prior policies for regularization similar to that of the Stein variational policy gradient (SVPG) (SVPG paper available at: https://arxiv.org/ab…
-
Hi author, your code is just wonderful and it help me a lot on building deep reinforcement learning system for my project. But I found a mistake in the following code. When you print out steps,
> …
-
I'm trying to differentiate the MJX step function via the autograd function `jax.grad()` in JAX, like:
```
def step(vel, pos):
mjx_data = mjx.make_data(mjx_model)
mjx_data = mjx_data.replace(q…
-
In the results of Chapter 14 Deterministic policy gradients in the book,
why the training is not very stable and noisy?
-------------------
![擷取](https://user-images.githubusercontent.com/475557…
-
* Want a single policy-gradient agent (in PyTorch) to train on the SingleGoal game.
* started over with the policy gradient agent myself instead of trying to aggregate existing code.
* had origi…
-
In this example https://github.com/keras-team/keras-io/blob/master/examples/rl/actor_critic_cartpole.py, the gradient for the actor is defined as the gradient of loss $L = \sum \ln\pi (reward-value)$.…
-
The Soft Actor-Critic paper ([arXiv v2](https://arxiv.org/abs/1801.01290)) says, in the last paragraph on page 5:
> We then use the minimum of the Q-functions for the value gradient in Equation 6 a…
-
Thanks for providing the pytorch version of option critic. I want to ask why don't we clean replay buffer after each episode for on-policy policy gradient update? I think both algorithm 1 in the paper…
-
The rough idea is the following:
- Share policy network.
- Collect experience asynchronously.
- Accumulate gradient.
- Update policy network.
**Related issues:**
#391 #438