-
COPHY: Counterfactual Learning of Physical Dynamics
Understanding causes and effects in mechanical systems is an essential c...
read it
-
Causal Induction from Visual Observations for Goal Directed Tasks
Causal reasoning has been an indispensable capability for humans and oth...
read it
-
Learning to Simulate Human Movement
Modeling how human moves on the space is useful for policy-making in tra...
read it
-
Causal Reasoning from Meta-reinforcement Learning
Discovering and exploiting the causal structure in the environment is a ...
read it
-
Towards intervention-centric causal reasoning in learning agents
Interventions are central to causal learning and reasoning. Yet ultimate...
read it
-
Counterfactual Predictions under Runtime Confounding
Algorithms are commonly used to predict outcomes under a particular deci...
read it
-
Recurrent World Models Facilitate Policy Evolution
A generative recurrent neural network is quickly trained in an unsupervi...
read it
Causal World Models by Unsupervised Deconfounding of Physical Dynamics
The capability of imagining internally with a mental model of the world is vitally important for human cognition. If a machine intelligent agent can learn a world model to create a "dream" environment, it can then internally ask what-if questions – simulate the alternative futures that haven't been experienced in the past yet – and make optimal decisions accordingly. Existing world models are established typically by learning spatio-temporal regularities embedded from the past sensory signal without taking into account confounding factors that influence state transition dynamics. As such, they fail to answer the critical counterfactual questions about "what would have happened" if a certain action policy was taken. In this paper, we propose Causal World Models (CWMs) that allow unsupervised modeling of relationships between the intervened observations and the alternative futures by learning an estimator of the latent confounding factors. We empirically evaluate our method and demonstrate its effectiveness in a variety of physical reasoning environments. Specifically, we show reductions in sample complexity for reinforcement learning tasks and improvements in counterfactual physical reasoning.
READ FULL TEXT
Comments
There are no comments yet.