Related papers: Failure-aware Policy Learning for Self-assessable …
Policy steering is an emerging way to adapt robot behaviors at deployment-time: a learned verifier analyzes low-level action samples proposed by a pre-trained policy (e.g., diffusion policy) and selects only those aligned with the task.…
Learning to evaluate and improve policies is a core problem of Reinforcement Learning (RL). Traditional RL algorithms learn a value function defined for a single policy. A recently explored competitive alternative is to learn a single value…
One of the great promises of robot learning systems is that they will be able to learn from their mistakes and continuously adapt to ever-changing environments. Despite this potential, most of the robot learning systems today are deployed…
Multi-robot coordination is crucial for autonomous systems, yet real-world deployments often encounter various failures. These include both temporary and permanent disruptions in sensing and communication, which can significantly degrade…
To unbiasedly evaluate multiple target policies, the dominant approach among RL practitioners is to run and evaluate each target policy separately. However, this evaluation method is far from efficient because samples are not shared across…
Data-efficient learning algorithms are essential in many practical applications where data collection is expensive, e.g., in robotics due to the wear and tear. To address this problem, meta-learning algorithms use prior experience about…
Many reinforcement learning algorithms, particularly those that rely on return estimates for policy improvement, can suffer from poor sample efficiency and training instability due to high-variance return estimates. In this paper we…
We study the problem of policy repair for learning-based control policies in safety-critical settings. We consider an architecture where a high-performance learning-based control policy (e.g. one trained as a neural network) is paired with…
In many machine learning applications, there are multiple decision-makers involved, both automated and human. The interaction between these agents often goes unaddressed in algorithmic development. In this work, we explore a simple version…
Decision making for self-driving cars is usually tackled by manually encoding rules from drivers' behaviors or imitating drivers' manipulation using supervised learning techniques. Both of them rely on mass driving data to cover all…
Reinforcement learning algorithms describe how an agent can learn an optimal action policy in a sequential decision process, through repeated experience. In a given environment, the agent policy provides him some running and terminal…
We propose to learn to distinguish reversible from irreversible actions for better informed decision-making in Reinforcement Learning (RL). From theoretical considerations, we show that approximate reversibility can be learned through a…
Deep reinforcement learning algorithms require large amounts of experience to learn an individual task. While in principle meta-reinforcement learning (meta-RL) algorithms enable agents to learn new skills from small amounts of experience,…
Policy learning for partially observed control tasks requires policies that can remember salient information from past observations. In this paper, we present a method for learning policies with internal memory for high-dimensional,…
In this work we present a method for learning a reactive policy for a simple dynamic locomotion task involving hard impact and switching contacts where we assume the contact location and contact timing to be unknown. To learn such a policy,…
A fundamental objective in intelligent robotics is to move towards lifelong learning robot that can learn and adapt to unseen scenarios over time. However, continually learning new tasks would introduce catastrophic forgetting problems due…
Reinforcement learning (RL) has demonstrated its ability to solve high dimensional tasks by leveraging non-linear function approximators. However, these successes are mostly achieved by 'black-box' policies in simulated domains. When…
Off-policy learning from multistep returns is crucial for sample-efficient reinforcement learning, particularly in the experience replay setting now commonly used with deep neural networks. Classically, off-policy estimation bias is…
Off-policy learning methods seek to derive an optimal policy directly from a fixed dataset of prior interactions. This objective presents significant challenges, primarily due to the inherent distributional shift and value function…
Policy evaluation estimates the performance of a policy by (1) collecting data from the environment and (2) processing raw data into a meaningful estimate. Due to the sequential nature of reinforcement learning, any improper data-collecting…