Standard MARL algorithms collapse on the Manitokan hidden-gift task, while actor-critic agents with action history and a self-correction term reliably learn to leave the key.
Effective choice in the prisoner's dilemma
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
The challenge of hidden gifts in multi-agent reinforcement learning
Standard MARL algorithms collapse on the Manitokan hidden-gift task, while actor-critic agents with action history and a self-correction term reliably learn to leave the key.