A major bottleneck for developing general reinforcement learning agents is determining
rewards that will yield desirable behaviors under various circumstances. We introduce a …

Agents that can learn to imitate behaviours observed in video-without having direct access
to internal state or action information of the observed agent-are more suitable for learning in …

Training a high-dimensional simulated agent with an under-specified reward function often
leads the agent to learn physically infeasible strategies that are ineffective when deployed in …

Advances in Deep Reinforcement Learning have led to agents that perform well across a
variety of sensory-motor domains. In this work, we study the setting in which an agent must …

Reinforcement learning (RL) is a powerful technique to train an agent to perform a task.
However, an agent that is trained using RL is only capable of achieving the single task that …

As deep reinforcement learning driven by visual perception becomes more widely used
there is a growing need to better understand and probe the learned agents. Understanding …

Simulation is a crucial component of any robotic system. In order to simulate correctly, we
need to write complex rules of the environment: how dynamic agents behave, and how the …

Deep generative models for video primarily treat videos as visual representations of agents
(eg, people or objects) performing actions, often overlooking the underlying intentions …

Reinforcement learning (RL) is a powerful technique to train an agent to perform a task;
however, an agent that is trained using RL is only capable of achieving the single task that is …

Reinforcement learning is a powerful framework for robots to acquire skills from experience,
but often requires a substantial amount of online data collection. As a result, it is difficult to …