Marco Pleines
Marco Pleines
I trained a model which can get a mean reward of 7 for solving seed 34 if realtime_mode is disabled. If I set realtime_mode to true to observe the agent...
Is there a possibiity to print the current floor? I'd like to track the mean floor for my training statistics. The property _floor is set to None as long as...
**Is your feature request related to a problem? Please describe.** Changing the Decision Period of the Decision Requester at runtime freezes the agent instead of firing an exception **Describe the...
This issue might be related to #55 Hello everybody, I basically followed your instructions, but made a few adjustments. The issue is that the notebook container doesn't respond. ``` jhub...
Hi @edbeeching thanks for your API! I've got two questions: In your paper you state that 12k interactions per second are recorded. How many environments ran in parallel for this...
Hey folks! I frequently follow rliable's guidelines to plot sample efficiency curves. I came across results now where 5 seeds of one experiment had large variance, but the bootstrapped confidence...
Hi! Is it possible to run multiple instances of these environments on one machine? I didn't find an example yet. Also, can this environment be run headless without using EGL...
Hi! I'd really love to reproduce the results from your paper "Generalization of Reinforcement Learners with Working and Episodic Memory". Is the source code somewhere available?
## Description Implementation of PPO with Transformer-XL as episodic memory. Based on this [repo](https://github.com/MarcoMeter/episodic-transformer-memory-ppo) and [paper](https://arxiv.org/abs/2309.17207). ## Types of changes - [ ] Bug fix - [ ] New feature...
## Problem Description After installing the dependencies via poetry inside a conda environment, any use of poetry results in `ModuleNotFoundError: No module named 'tomli'`. ## Checklist - [x] I have...