GitHub - oliehoek-research/interactive_agents: Reinforcement learning agents which adapt online via human interaction

Interactive Agents

Reinforcement learning for human-AI interaction.

Name		Name	Last commit message	Last commit date
Latest commit History 143 Commits
amanuensis @ 6b892d2		amanuensis @ 6b892d2
experiments		experiments
interactive_agents		interactive_agents
junk		junk
.gitignore		.gitignore
.gitmodules		.gitmodules
LICENSE		LICENSE
README.md		README.md
array_job.sh		array_job.sh
coordination_gauntlet.py		coordination_gauntlet.py
cross_evaluate.py		cross_evaluate.py
decision_transformer_test.py		decision_transformer_test.py
from_grid_to_yamls.py		from_grid_to_yamls.py
jpc.py		jpc.py
listener_gauntlet.py		listener_gauntlet.py
plot.py		plot.py
requirements.txt		requirements.txt
scalar_jpc.py		scalar_jpc.py
scalar_jpc_difference.py		scalar_jpc_difference.py
setup.py		setup.py
singularity_recipe.def		singularity_recipe.def
slurm_run.py		slurm_run.py
slurm_setup.py		slurm_setup.py
slurm_train.py		slurm_train.py
speaker_listener_gauntlet.py		speaker_listener_gauntlet.py
train.py		train.py
train.sh		train.sh
train_local.py		train_local.py
tune.py		tune.py
tune_cross_eval.py		tune_cross_eval.py
visualize.py		visualize.py