An attention-augmented actor-critic agent learns to dynamically weight multiple environment views by importance and outperforms baselines on TORCS and three other 3D simulators under noise and partial observability.
Multi- agent actor-critic for mixed cooperative-competitive envi- ronments
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
An Actor-Critic-Attention Mechanism for Deep Reinforcement Learning in Multi-view Environments
An attention-augmented actor-critic agent learns to dynamically weight multiple environment views by importance and outperforms baselines on TORCS and three other 3D simulators under noise and partial observability.