Public articles linked to the same research event.
arXiv The work analyzes temporal abstraction as a mechanism to mitigate the spectral mismatch in forward-backward (FB) representations, showing by characterizing the spectral properties of the transition operator that temporal abstraction acts analogously to a low-pass filter suppressing high-frequency spectral components, thereby reducing the effective rank of the induced successor representation while preserving a formal bound on the value function error, and empirically showing that this alignment is a key factor for stable FB learning at high discount factors.
The work analyzes temporal abstraction as a mechanism to mitigate the spectral mismatch in forward-backward (FB) representations, showing by characterizing the spectral properties of the transition operator that temporal abstraction acts analogously to a low-pass filter suppressing high-frequency spectral components, thereby reducing the effective rank of the induced successor representation while preserving a formal bound on the value function error, and empirically showing that this alignment is a key factor for stable FB learning at high discount factors.
The work analyzes temporal abstraction as a mechanism to mitigate the spectral mismatch in forward-backward (FB) representations, showing by characterizing the spectral properties of the transition operator that temporal abstraction acts analogously to a low-pass filter suppressing high-frequency spectral components, thereby reducing the effective rank of the induced successor representation while preserving a formal bound on the value function error, and empirically showing that this alignment is a key factor for stable FB learning at high discount factors.
The work analyzes temporal abstraction as a mechanism to mitigate the spectral mismatch in forward-backward (FB) representations, showing by characterizing the spectral properties of the transition operator that temporal abstraction acts analogously to a low-pass filter suppressing high-frequency spectral components, thereby reducing the effective rank of the induced successor representation while preserving a formal bound on the value function error, and empirically showing that this alignment is a key factor for stable FB learning at high discount factors.