SAMA

The code of the AISTATS'25 paper "Multi-Agent Credit Assignment with Pretrained Language Models".

Name		Name	Last commit message	Last commit date
Latest commit History 22 Commits
.gitignore		.gitignore
LICENSE		LICENSE
README.md		README.md
example_goal_decomp_allocate_minirts.txt		example_goal_decomp_allocate_minirts.txt
example_goal_gen_decomp_overcooked.txt		example_goal_gen_decomp_overcooked.txt
example_self_reflection_1_overcooked.txt		example_self_reflection_1_overcooked.txt
example_self_reflection_2_overcooked.txt		example_self_reflection_2_overcooked.txt
example_self_reflection_minirts.txt		example_self_reflection_minirts.txt
example_subgoal_allocate.txt		example_subgoal_allocate.txt
goal_decomp_allocate_minirts.txt		goal_decomp_allocate_minirts.txt
goal_gen_decomp_overcooked.txt		goal_gen_decomp_overcooked.txt
goal_generation.txt		goal_generation.txt
interact_obj_extraction.txt		interact_obj_extraction.txt
q_game.txt		q_game.txt
q_rel.txt		q_rel.txt
reward_design.txt		reward_design.txt
sa_translation.txt		sa_translation.txt
self_reflection_minirts.txt		self_reflection_minirts.txt
self_reflection_overcooked.txt		self_reflection_overcooked.txt
subgoal_allocate_overcooked.txt		subgoal_allocate_overcooked.txt

Provide feedback