We develop a transformer-based sequence-to-sequence model that recovers
...
Natural laws are often described through differential equations yet find...
Credit assignment is one of the central problems in reinforcement learni...
Symbolic equations are at the core of scientific discovery. The task of
...
Despite recent successes of reinforcement learning (RL), it remains a
ch...
In this paper, we investigate the principle that `good explanations are ...
Standard planners for sequential decision making (including Monte Carlo
...
We introduce a method which enables a recurrent dynamics model to be
tem...