A perspective paper that advocates direct, post hoc interpretability for multi-agent deep reinforcement learning and offers a taxonomy of where those methods might apply.
Interpretable Brain-Inspired Representations Improve RL Performance on Visual Navigation Tasks
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
Visual navigation requires a whole range of capabilities. A crucial one of these is the ability of an agent to determine its own location and heading in an environment. Prior works commonly assume this information as given, or use methods which lack a suitable inductive bias and accumulate error over time. In this work, we show how the method of slow feature analysis (SFA), inspired by neuroscience research, overcomes both limitations by generating interpretable representations of visual data that encode location and heading of an agent. We employ SFA in a modern reinforcement learning context, analyse and compare representations and illustrate where hierarchical SFA can outperform other feature extractors on navigation tasks.
fields
cs.AI 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Perspectives for Direct Interpretability in Multi-Agent Deep Reinforcement Learning
A perspective paper that advocates direct, post hoc interpretability for multi-agent deep reinforcement learning and offers a taxonomy of where those methods might apply.