rainbow-is-all-you-need

rainbow-is-all-you-need copied to clipboard

clear momory during n_step_learning

1

In the training loop, it might make sense to call self.memory_n_step.n_step_buffer.clear() when an episode is done to avoid (final->initial) transitions.

PigUnderRoof

curiosity

4

experiment curiosity, use icm to add intrinsic rewards. Deepak Pathak, Pulkit Agrawal, Alexei A. Efros and Trevor Darrell. Curiosity-driven Exploration by Self-supervised Prediction. In ICML 2017.

zhchaoo

bias_sigma initialization in noisy net

1

According to Sec. 3.2 in the paper "Noisy Networks for Exploration", sigmas are initialized to a constant `sigma / sort(p)`. However, in this implementation, `self.bias_sigma.data.fill_(self.std_init / math.sqrt(self.out_features))` is realized. Is...

kentropy

Bumps [jupyterlab](https://github.com/jupyterlab/jupyterlab) from 3.2.6 to 3.6.7. Release notes Sourced from jupyterlab's releases. v3.6.7 3.6.7 (Full Changelog) Security fixes Potential authentication and CSRF tokens leak in JupyterLab (GHSA-44cc-43rp-5947) Bugs fixed [3.6.x]...

dependabot[bot]

In the DQNAgent, particularly in the step method, there seems to be a potential issue in properly distinguishing between termination and truncation, as suggested by the Gymnasium documentation available at...

carlos-UPC-AI

Save/Load capabilities

2

Hey, If I may ask for the addition of a "Load" and "Save" to the Rainbow model, it will help me a lot. If such capabilities already exist, please let...

chensh3

Hi, I have seen that during test time, you select action with noise i.e either with noisy nets or epsilon greedy. Is that the right thing to do during test...

nil123532

Shouldn't `self.beta = self.beta + fraction * (1.0 - self.beta)` be changed to `self.beta = self.beta_initial + fraction * (1.0 - self.beta_initial)`?

xxxgodon