evolution-strategies-starter

evolution-strategies-starter copied to clipboard

Load

1

Hello, is there a way to load a snapshot to continue optimizing an aborted run? Thanks, Ernst

ErnstTmp

Hi, I was wondering if you've experimented with trying to increase the sampling efficiency by adding Prioritized Experience Replay? Am working on adding your existing buffer code from the baseline's...

ghost

Hi, I really like this code - could you may be publish an ATARI policy? Thanks and kind regards Ernst

ErnstTmp

Doesn't work for continuous_mountain_car

6

Hello, the algo doesn't work for continuous_mountain_car, because it's reward is -pow(action[0],2)*0.1. What means, the car's initial state is a local max reward, all the exploration will decrease the reward...

joyousrabbit

Problems with viz.py

2

I'm having a bit of trouble with `viz.py` When I run it like so: sudo python3 -m scripts.viz Humanoid-v1 /tmp/es_master_25626/snapshot_iter00000_rew279.h5 --record --stochastic I get errors like this: ``` Traceback (most...

truell20

Hi, Could you please release an example config file for Atari games as well? Thanks!

sahiliitm