Henry

Optimise RL Code

1

## 🚀 Feature There seems to be fair few inefficiencies in the RL model code. In both the VPG and DQN code, the network is computed twice, once to generate...

Add A2C, PPO and other modern standard RL Algorithms

3

## 🚀 Feature The RL section of bolts currently only includes variants of DQN and VPG and lacks some of the more modern RL algorithms. Adding PPO, A2C, curiosity exploration...

Code duplication in vanilla policy gradients

5

## 🐛 Bug It seems like there's 2 near identical implementations of VPG, with only a small change in loss function https://github.com/PyTorchLightning/pytorch-lightning-bolts/blob/master/pl_bolts/models/rl/reinforce_model.py https://github.com/PyTorchLightning/pytorch-lightning-bolts/blob/master/pl_bolts/models/rl/vanilla_policy_gradient_model.py

Random JSON error

7

Hey I've some code which loops through some Yahoo tickers and fetches today's OHLCV It seems to randomly stop and give me this: Traceback (most recent call last): File "fetch.py",...

Install script fails if klipper service using non-default name

1

### K-Shake&Tune module branch - [X] I confirm using the main branch ### Version 66f5e32e4c8930afab278fcd898b47c227cc464c ### Describe the bug and expected behavior For cases such as running multiple klipper instances...