Related papers: Learning Future Representation with Synthetic Obse…
Reinforcement Learning (RL) has made significant strides in enabling artificial agents to learn diverse behaviors. However, learning an effective policy often requires a large number of environment interactions. To mitigate sample…
Reinforcement learning is able to solve complex sequential decision-making tasks but is currently limited by sample efficiency and required computation. To improve sample efficiency, recent work focuses on model-based RL which interleaves…
Reinforcement learning (RL) in the real world necessitates the development of procedures that enable agents to explore without causing harm to themselves or others. The most successful solutions to the problem of safe RL leverage offline…
Leveraging offline data is a promising way to improve the sample efficiency of online reinforcement learning (RL). This paper expands the pool of usable data for offline-to-online RL by leveraging abundant non-curated data that is…
Improving sample efficiency is central to Reinforcement Learning (RL), especially in environments where the rewards are sparse. Some recent approaches have proposed to specify reward functions as manually designed or learned reward…
Effective feature selection, representation and transformation are principal steps in machine learning to improve prediction accuracy, model generalization and computational efficiency. Reinforcement learning provides a new perspective…
Autonomous robots require high degrees of cognitive and motoric intelligence to come into our everyday life. In non-structured environments and in the presence of uncertainties, such degrees of intelligence are not easy to obtain.…
Deep reinforcement learning (DRL) requires the collection of interventional data, which is sometimes expensive and even unethical in the real world, such as in the autonomous driving and the medical field. Offline reinforcement learning…
In real-world applications with large state and action spaces, reinforcement learning (RL) typically employs function approximations to represent core components like the policies, value functions, and dynamics models. Although powerful…
The standard approach to modern self-supervised learning is to generate random views through data augmentations and minimise a loss computed from the representations of these views. This inherently encourages invariance to the…
Abstraction is key to scaling up reinforcement learning (RL). However, autonomously learning abstract state and action representations to enable transfer and generalization remains a challenging open problem. This paper presents a novel…
Demonstration-guided reinforcement learning (RL) is a promising approach for learning complex behaviors by leveraging both reward feedback and a set of target task demonstrations. Prior approaches for demonstration-guided RL treat every new…
Robots could learn their own state and world representation from perception and experience without supervision. This desirable goal is the main focus of our field of interest, state representation learning (SRL). Indeed, a compact…
Sequential decision-making agents struggle with long horizon tasks, since solving them requires multi-step reasoning. Most reinforcement learning (RL) algorithms address this challenge by improved credit assignment, introducing memory…
Visual program synthesis is a promising approach to exploit the reasoning abilities of large language models for compositional computer vision tasks. Previous work has used few-shot prompting with frozen LLMs to synthesize visual programs.…
In reinforcement learning (RL), it is easier to solve a task if given a good representation. While deep RL should automatically acquire such good representations, prior work often finds that learning representations in an end-to-end fashion…
This paper investigates how to incorporate expert observations (without explicit information on expert actions) into a deep reinforcement learning setting to improve sample efficiency. First, we formulate an augmented policy loss combining…
Offline reinforcement learning (RL) can in principle synthesize more optimal behavior from a dataset consisting only of suboptimal trials. One way that this can happen is by "stitching" together the best parts of otherwise suboptimal…
Recent advances at the intersection of reinforcement learning (RL) and visual intelligence have enabled agents that not only perceive complex visual scenes but also reason, generate, and act within them. This survey offers a critical and…
Reinforcement Learning (RL) has been shown to significantly boost reasoning capabilities of large language models (LLMs) in math, coding, and multi-hop reasoning tasks. However, RL fine-tuning requires abundant high-quality verifiable data,…