A key challenge in intelligent robotics is creating robots that are capable of directly
interacting with the world around them to achieve their goals. The last decade has seen …

A generally intelligent agent faces a dilemma: it requires a complex sensorimotor space to
be capable of solving a wide range of problems, but many tasks are only feasible given the …

Temporal abstraction is key to scaling up learning and planning in reinforcement learning.
While planning with temporally extended actions is well understood, creating such …

We consider the problem of constructing abstract representations for planning in high-
dimensional, continuous environments. We assume an agent equipped with a collection of …

Deep reinforcement learning has achieved many impressive results in recent years.
However, tasks with sparse rewards or long horizons continue to pose significant …

Reinforcement learning offers to robotics a framework and set of tools for the design of
sophisticated and hard-to-engineer behaviors. Conversely, the challenges of robotic …

We describe CST, an online algorithm for constructing skill trees from demonstration
trajectories. CST segments a demonstration trajectory into a chain of component skills …

Synchronizing decisions across multiple agents in realistic settings is problematic since it
requires agents to wait for other agents to terminate and communicate about termination …

Most common navigation tasks in human environments require auxiliary arm interactions, eg
opening doors, pressing buttons and pushing obstacles away. This type of navigation tasks …

Many Reinforcement Learning (RL) approaches use joint control signals (positions,
velocities, torques) as action space for continuous control tasks. We propose to lift the action …