Related papers: Adaptive Language-Guided Abstraction from Contrast…
Agents that can learn to imitate given video observation -- \emph{without direct access to state or action information} are more applicable to learning in the natural world. However, formulating a reinforcement learning (RL) agent that…
Humans effortlessly "program" one another by communicating goals and desires in natural language. In contrast, humans program robotic behaviours by indicating desired object locations and poses to be achieved, by providing RGB images of…
Existing approaches to reward inference from behavior typically assume that humans provide demonstrations according to specific models of behavior. However, humans often indicate their goals through a wide range of behaviors, from actions…
To learn manipulation skills, robots need to understand the features of those skills. An easy way for robots to learn is through Learning from Demonstration (LfD), where the robot learns a skill from an expert demonstrator. While the main…
Reward function design and exploration time are arguably the biggest obstacles to the deployment of reinforcement learning (RL) agents in the real world. In many real-world tasks, designing a reward function takes considerable hand…
A key challenge in reward learning from human input is that desired agent behavior often changes based on context. For example, a robot must adapt to avoid a stove once it becomes hot. We observe that while high-level preferences (e.g.,…
When robots learn reward functions using high capacity models that take raw state directly as input, they need to both learn a representation for what matters in the task -- the task ``features" -- as well as how to combine these features…
Learning from Demonstration~(LfD) should capture not only how a task is executed, but also its high-level task structure that explains the demonstrated behavior. As robots become more autonomous, such task representations must be…
Effective human-robot interaction, such as in robot learning from human demonstration, requires the learning agent to be able to ground abstract concepts (such as those contained within instructions) in a corresponding high-dimensional…
Robots can learn from humans by asking questions. In these questions the robot demonstrates a few different behaviors and asks the human for their favorite. But how should robots choose which questions to ask? Today's robots optimize for…
Explaining the behaviour of intelligent agents learned by reinforcement learning (RL) to humans is challenging yet crucial due to their incomprehensible proprioceptive states, variational intermediate goals, and resultant unpredictability.…
We introduce Behavior from Language and Demonstration (BLADE), a framework for long-horizon robotic manipulation by integrating imitation learning and model-based planning. BLADE leverages language-annotated demonstrations, extracts…
We present a framework for learning human user models from joint-action demonstrations that enables the robot to compute a robust policy for a collaborative task with a human. The learning takes place completely automatically, without any…
Explanations constitute an important aspect of successful human robot interactions and can enhance robot understanding. To improve the understanding of the robot, we have developed four levels of explanation (LOE) based on two questions:…
We study the problem of cross-embodiment inverse reinforcement learning, where we wish to learn a reward function from video demonstrations in one or more embodiments and then transfer the learned reward to a different embodiment (e.g.,…
Scaling up test-time compute, by generating multiple independent solutions and selecting or aggregating among them, has become a central paradigm for improving large language models (LLMs) on challenging reasoning tasks. While most prior…
Recent work has shown that deep reinforcement-learning agents can learn to follow language-like instructions from infrequent environment rewards. However, this places on environment designers the onus of designing language-conditional…
For a robot to be called socially intelligent, it must be able to infer users internal states from their current behaviour, predict the users future behaviour, and if required, respond appropriately. In this work, we investigate how robots…
Generating complex behaviors that satisfy the preferences of non-expert users is a crucial requirement for AI agents. Interactive reward learning from trajectory comparisons (a.k.a. RLHF) is one way to allow non-expert users to convey…
In the learning from demonstration (LfD) paradigm, understanding and evaluating the demonstrated behaviors plays a critical role in extracting control policies for robots. Without this knowledge, a robot may infer incorrect reward functions…