A multi-agent RL agent with parallel candidate policies and a learned regret matrix outperforms MADDPG and COMA in two competitive environments.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2019 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Competitive Multi-Agent Deep Reinforcement Learning with Counterfactual Thinking
A multi-agent RL agent with parallel candidate policies and a learned regret matrix outperforms MADDPG and COMA in two competitive environments.