[1910.01751] Causal Induction from Visual Observations for Goal Directed Tasks
Our key insight is that by leveraging iterative predictions and attention bottlenecks, it facilitates our causal induction model and goal-conditioned policy to focus on the relevant part of the causal graph
Abstract: Causal reasoning has been an indispensable capability for humans and other
intelligent animals to interact with the physical world. In this work, we
propose to endow an artificial agent with the capability of causal reasoning
for completing goal-directed tasks. We develop learning-based approaches to
inducing causal knowledge in the form of directed acyclic graphs, which can be
used to contextualize a learned goal-conditional policy to perform tasks in
novel environments with latent causal structures. We leverage attention
mechanisms in our causal induction model and goal-conditional policy, enabling
us to incrementally generate the causal graph from the agent's visual
observations and to selectively use the induced graph for determining actions.
Our experiments show that our method effectively generalizes towards completing
new tasks in novel environments with previously unseen causal structures.