Accurately inferring Gene Regulatory Networks (GRNs) is a critical and
c...
Deep reinforcement learning repeatedly succeeds in closed, well-defined
...
State of the art reinforcement learning has enabled training agents on t...
NeRF provides unparalleled fidelity of novel view synthesis: rendering a...
Effective decision making involves flexibly relating past experiences an...
The fundamental challenge in causal induction is to infer the underlying...
Most deep reinforcement learning (RL) algorithms distill experience into...
One of the key promises of model-based reinforcement learning is the abi...
We propose a novel policy update that combines regularized policy
optimi...
Since the earliest days of reinforcement learning, the workhorse method ...
In multi-agent reinforcement learning, the problem of learning to act is...
How sensitive should machine learning models be to input changes? We tac...
Credit assignment in reinforcement learning is the problem of measuring ...
Model-based planning is often thought to be necessary for deep, careful
...
Intelligent robots need to achieve abstract objectives using concrete,
s...
Recent work in deep reinforcement learning (RL) has produced algorithms
...
Standard planners for sequential decision making (including Monte Carlo
...
Value estimation is a critical component of the reinforcement learning (...
In reinforcement learning, we can learn a model of future observations a...
We introduce "Search with Amortized Value Estimates" (SAVE), an approach...
A plethora of problems in AI, engineering and the sciences are naturally...
We investigate using reinforcement learning agents as generative models ...
The field of reinforcement learning (RL) is facing increasingly challeng...
Stochastic computation graphs (SCGs) provide a formalism to represent
st...
We introduce two novel tree search algorithms that use a policy to guide...
Learning policies on data synthesized by models can in principle quench ...
Memory-based neural networks model temporal data by leveraging an abilit...
Planning problems are among the most important and well-studied problems...
A key challenge in model-based reinforcement learning (RL) is to synthes...
We introduce Imagination-Augmented Agents (I2As), a novel architecture f...
Conventional wisdom holds that model-based planning is a powerful approa...
From just a glance, humans can make rich predictions about the future st...
We present a framework for efficient inference in structured image model...
Being able to reason in an environment with a large number of discrete
a...
We present a new algorithm for approximate inference in probabilistic
pr...