Recent in-context reinforcement learning literature is organized into a taxonomy covering pretraining methods, context construction, test-time performance, theory, and architectures, with no new experiments or theory introduced.
Learning to Cooperate with Unseen Agent via Meta-Reinforcement Learning
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
Ad hoc teamwork problem describes situations where an agent has to cooperate with previously unseen agents to achieve a common goal. For an agent to be successful in these scenarios, it has to have a suitable cooperative skill. One could implement cooperative skills into an agent by using domain knowledge to design the agent's behavior. However, in complex domains, domain knowledge might not be available. Therefore, it is worthwhile to explore how to directly learn cooperative skills from data. In this work, we apply meta-reinforcement learning (meta-RL) formulation in the context of the ad hoc teamwork problem. Our empirical results show that such a method could produce robust cooperative agents in two cooperative environments with different cooperative circumstances: social compliance and language interpretation. (This is a full paper of the extended abstract version.)
fields
cs.LG 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
A Survey of In-Context Reinforcement Learning
Recent in-context reinforcement learning literature is organized into a taxonomy covering pretraining methods, context construction, test-time performance, theory, and architectures, with no new experiments or theory introduced.