Similar to humans, RL agents use interactive learning to successfully obtain satisfactory
decision strategies. However, in many cases, it is desirable to learn directly from …

Deep reinforcement learning (DRL) has gained great success by learning directly from high-
dimensional sensory inputs, yet is notorious for the lack of interpretability. Interpretability of …

Object-based factorizations provide a useful level of abstraction for interacting with the
world. Building explicit object representations, however, often requires supervisory signals …

Reinforcement learning (RL) studies how an agent comes to achieve reward in an
environment through interactions over time. Recent advances in machine RL have …

We present COIL (Counterfactual Object Interaction Learning), a novel way of learning skills
of object interactions on entity-centric environments. The goal is to learn primitive behaviors …

Current image-based reinforcement learning (RL) algorithms typically operate on the whole
image without performing object-level reasoning. This leads to inefficient goal sampling and …

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" …

Model-based reinforcement learning (RL) is appealing because (i) it enables planning and
thus more strategic exploration, and (ii) by decoupling dynamics from rewards, it enables …

Задачи планирования поведения и обучения принятию решений в динамической среде
в системах управления интеллектуальными агентами обычно разделяют и …

Evaluation of deep reinforcement learning (RL) is inherently challenging. In particular,
learned policies are largely opaque, and hypotheses about the behavior of deep RL agents …