Related papers: When to Ask for Help: Proactive Interventions in A…

We introduce a novel repeated Inverse Reinforcement Learning problem: the agent has to act on behalf of a human in a sequence of tasks and wishes to minimize the number of tasks that it surprises the human by acting suboptimally with…

The main challenge of multiagent reinforcement learning is the difficulty of learning useful policies in the presence of other simultaneously learning agents whose changing behaviors jointly affect the environment's transition and reward…

Artificial intelligence (AI) assistants are increasingly embedded in workplace tools, raising the question of how initiative-taking shapes adoption. Prior work highlights trust and expectation mismatches as barriers, but the underlying…

Reinforcement learning (RL) is a general framework for adaptive control, which has proven to be efficient in many domains, e.g., board games, video games or autonomous vehicles. In such problems, an agent faces a sequential decision-making…

In recent years, a myriad of superlative works on intelligent robotics policies have been done, thanks to advances in machine learning. However, inefficiency and lack of transfer ability hindered algorithms from pragmatic applications,…

Reinforcement learning algorithms discover policies that maximize reward, but do not necessarily guarantee safety during learning or execution phases. We introduce a new approach to learn optimal policies while enforcing properties…

Random exploration is one of the main mechanisms through which reinforcement learning (RL) finds well-performing policies. However, it can lead to undesirable or catastrophic outcomes when learning online in safety-critical environments. In…

Reinforcement learning (RL) requires skillful definition and remarkable computational efforts to solve optimization and control problems, which could impair its prospect. Introducing human guidance into reinforcement learning is a promising…

When deploying autonomous agents in the real world, we need effective ways of communicating objectives to them. Traditional skill learning has revolved around reinforcement and imitation learning, each with rigid constraints on the format…

Critical sectors of human society are progressing toward the adoption of powerful artificial intelligence (AI) agents, which are trained individually on behalf of self-interested principals but deployed in a shared environment. Short of…

The combination of deep neural network models and reinforcement learning algorithms can make it possible to learn policies for robotic behaviors that directly read in raw sensory inputs, such as camera images, effectively subsuming both…

Voice assistants have recently achieved remarkable commercial success. However, the current generation of these devices is typically capable of only reactive interactions. In other words, interactions have to be initiated by the user, which…

A long-term goal of reinforcement learning agents is to be able to perform tasks in complex real-world scenarios. The use of external information is one way of scaling agents to more complex problems. However, there is a general lack of…

Robotic manipulation stands as a largely unsolved problem despite significant advances in robotics and machine learning in the last decades. One of the central challenges of manipulation is partial observability, as the agent usually does…

Reinforcement learning agents have demonstrated remarkable achievements in simulated environments. Data efficiency poses an impediment to carrying this success over to real environments. The design of data-efficient agents calls for a…

Existing approaches in reinforcement learning train an agent to learn desired optimal behavior in an environment with rule based surrounding agents. In safety critical applications such as autonomous driving it is crucial that the rule…

Recent reinforcement learning (RL) algorithms have demonstrated impressive results in simulated driving environments. However, autonomous vehicles trained in simulation often struggle to work well in the real world due to the fidelity gap…

Current imitation learning techniques are too restrictive because they require the agent and expert to share the same action space. However, oftentimes agents that act differently from the expert can solve the task just as good. For…

Robotic assistants in long-term human-robot collaboration need to assist users under partial observations while leveraging cross-day interaction history. However, human traits and routines are often unknown at the beginning of…

Deep reinforcement learning has proven to be a great success in allowing agents to learn complex tasks. However, its application to actual robots can be prohibitively expensive. Furthermore, the unpredictability of human behavior in…