English
Related papers

Related papers: Learning Achievement Structure for Structured Expl…

200 papers

Many real-world domains are subject to a structured non-stationarity which affects the agent's goals and the environmental dynamics. Meta-reinforcement learning (RL) has been shown successful for training agents that quickly adapt to…

Machine Learning · Computer Science 2021-05-20 Riccardo Poiani , Andrea Tirinzoni , Marcello Restelli

We study the problem of learning exploration-exploitation strategies that effectively adapt to dynamic environments, where the task may change over time. While RNN-based policies could in principle represent such strategies, in practice…

Reward-free, unsupervised discovery of skills is an attractive alternative to the bottleneck of hand-designing rewards in environments where task supervision is scarce or expensive. However, current skill pre-training methods, like many RL…

Machine Learning · Computer Science 2022-03-22 Nur Muhammad Shafiullah , Lerrel Pinto

This work pushes the boundaries of learning-based methods in autonomous robot exploration in terms of environmental scale and exploration efficiency. We present HEADER, an attention-based reinforcement learning approach with hierarchical…

Robotics · Computer Science 2025-10-20 Yuhong Cao , Yizhuo Wang , Jingsong Liang , Shuhao Liao , Yifeng Zhang , Peizhuo Li , Guillaume Sartoretti

Reinforcement learning (RL) commonly relies on scalar rewards with limited ability to express temporal, conditional, or safety-critical goals, and can lead to reward hacking. Temporal logic expressible via the more general class of…

Artificial Intelligence · Computer Science 2025-11-26 Dominik Wagner , Leon Witzman , Luke Ong

A long-standing goal in AI is to develop agents capable of solving diverse tasks across a range of environments, including those never seen during training. Two dominant paradigms address this challenge: (i) reinforcement learning (RL),…

Machine Learning · Computer Science 2025-10-30 Vlad Sobal , Wancong Zhang , Kyunghyun Cho , Randall Balestriero , Tim G. J. Rudner , Yann LeCun

Reinforcement learning (RL) with sparse and deceptive rewards is challenging because non-zero rewards are rarely obtained. Hence, the gradient calculated by the agent can be stochastic and without valid information. Recent studies that…

Machine Learning · Computer Science 2024-02-08 Guojian Wang , Faguo Wu , Xiao Zhang , Jianxiang Liu

Recently, reinforcement learning (RL) has been used as a tool for finding failures in autonomous systems. During execution, the RL agents often rely on some domain-specific heuristic reward to guide them towards finding failures, but…

Machine Learning · Computer Science 2020-06-22 Mark Koren , Mykel J. Kochenderfer

Training models to map natural language instructions to programs given target world supervision only requires searching for good programs at training time. Search is commonly done using beam search in the space of partial programs or…

Computation and Language · Computer Science 2019-03-21 Dor Muhlgay , Jonathan Herzig , Jonathan Berant

Recent evidence suggests that frontier AI systems can exhibit agentic misalignment, generating and executing harmful actions derived from internally constructed goals, even without explicit user requests. Existing mitigation methods, such…

Artificial Intelligence · Computer Science 2026-04-28 Rong Xiang

Reinforcement learning is typically treated as a uniform, data-driven optimization process, where updates are guided by rewards and temporal-difference errors without explicitly exploiting global structure. In contrast, dynamic programming…

Machine Learning · Computer Science 2026-04-21 Ivo Nowak

Open-ended learning benefits immensely from the use of symbolic methods for goal representation as they offer ways to structure knowledge for efficient and transferable learning. However, the existing Hierarchical Reinforcement Learning…

Machine Learning · Computer Science 2024-12-20 Mehdi Zadem , Sergio Mover , Sao Mai Nguyen

Learning optimal policies from sparse feedback is a known challenge in reinforcement learning. Hindsight Experience Replay (HER) is a multi-goal reinforcement learning algorithm that comes to solve such tasks. The algorithm treats every…

Machine Learning · Computer Science 2020-01-14 Binyamin Manela

Large Language Model (LLM) agents are increasingly improved through interaction, yet most self-evolution methods adapt either the policy or the learning environment in isolation. We identify this structural gap as \emph{Agent-Environment…

Computation and Language · Computer Science 2026-05-26 Yihao Hu , Zhihao Wen , Xiujin Liu , Pan Wang , Xin Zhang , Wei Wu

Recent research on structured exploration placed emphasis on identifying novel states in the state space and incentivizing the agent to revisit them through intrinsic reward bonuses. In this study, we question whether the performance boost…

Machine Learning · Computer Science 2020-11-12 Sneha Aenugu

Recent advances in Reinforcement Learning with Verifiable Rewards (RLVR) have demonstrated significant potential in single-turn reasoning tasks. With the paradigm shift toward self-evolving agentic learning, models are increasingly expected…

Artificial Intelligence · Computer Science 2026-04-21 Xinshun Feng , Xinhao Song , Lijun Li , Gongshen Liu , Jing Shao

Exploration in reinforcement learning (RL) remains an open challenge. RL algorithms rely on observing rewards to train the agent, and if informative rewards are sparse the agent learns slowly or may not learn at all. To improve exploration…

Machine Learning · Computer Science 2024-11-12 Simone Parisi , Alireza Kazemipour , Michael Bowling

Exploration is an essential component of reinforcement learning algorithms, where agents need to learn how to predict and control unknown and often stochastic environments. Reinforcement learning agents depend crucially on exploration to…

Machine Learning · Computer Science 2021-09-03 Susan Amin , Maziar Gomrokchi , Harsh Satija , Herke van Hoof , Doina Precup

This paper presents an approach for autonomous docking of a fully actuated autonomous surface vessel using expert demonstration data. We frame the docking problem as an imitation learning task and employ inverse reinforcement learning (IRL)…

Robotics · Computer Science 2024-11-13 Akash Vijayakumar , Atmanand M A , Abhilash Somayajula

The objective of many real-world tasks is complex and difficult to procedurally specify. This makes it necessary to use reward or imitation learning algorithms to infer a reward or policy directly from human data. Existing benchmarks for…

Machine Learning · Computer Science 2020-12-03 Pedro Freire , Adam Gleave , Sam Toyer , Stuart Russell