lb-foraging
lb-foraging copied to clipboard
semitable
Level-based Foraging (LBF): A multi-agent environment for RL
Minor fixes that ensure the package works with newer versions of Numpy. Also sets `Pyglet
I wrote a PettingZoo implementation of LBF. Perhaps one day we could get it featured on the PettingZoo website, which would be good for visibility. This might be a bit...
how can I set players as q_agent? I want to use other types of agents
Changes made: Python3.10 and Numpy Update The repo is now compatible with python 3.10. The syntax/function calls have been updated to work with the newer version of Numpy. For instance,...
In the current version of LBF an agent gets only one value as a reward after each step. If agents had several resources they could collect in the environment could...
When installing `lb-foraging` with certain versions of `gym`, the import hangs for a (very) long time. Consider a simple script, `import_tests.py`: ```py from time import time start = time() import...
When I render the view of the experiment, I met the following problem, is there anyone else had met the same problem before?  How could I render the test...
- by default randomisation is turned on, to ensure consistency with prior versions - without randomisation, agents are spawned in corners of maps and food are spawned in the center...
File "/home/lenovo/anaconda3/envs/env_rl_mujoco/lib/python3.9/site-packages/lbforaging/foraging/rendering.py", line 134, in _draw_grid batch.add( AttributeError: 'Batch' object has no attribute 'add' batch is a instance of pyglet as follow batch = pyglet.graphics.Batch() for r in range(self.rows +...
This PR removes the deprecated `gym==0.21` dependency of LBF and replaces it with the maintained `gymnasium` library. This causes slight changes in the interface with the environment that are documented...