中文
相关论文

相关论文: From Language to Goals: Inverse Reinforcement Lear…

200 篇论文

Humans generally use natural language to communicate task requirements to each other. Ideally, natural language should also be usable for communicating goals to autonomous machines (e.g., robots) to minimize friction in task specification.…

机器学习 · 计算机科学 2020-12-17 Li Zhou , Kevin Small

Mapping natural language instructions to programs that computers can process is a fundamental challenge. Existing approaches focus on likelihood-based training or using reinforcement learning to fine-tune models based on a single reward. In…

计算与语言 · 计算机科学 2021-10-05 Sayan Ghosh , Shashank Srivastava

Reinforcement learning (RL), particularly in sparse reward settings, often requires prohibitively large numbers of interactions with the environment, thereby limiting its applicability to complex problems. To address this, several prior…

机器学习 · 计算机科学 2020-11-20 Prasoon Goyal , Scott Niekum , Raymond J. Mooney

Reinforcement Learning (RL) is a promising approach for solving various control, optimization, and sequential decision making tasks. However, designing reward functions for complex tasks (e.g., with multiple objectives and safety…

人工智能 · 计算机科学 2021-07-23 Xuan Zhao , Marcos Campos

While reinforcement learning provides an appealing formalism for learning individual skills, a general-purpose robotic system must be able to master an extensive repertoire of behaviors. Instead of learning a large collection of skills…

机器人学 · 计算机科学 2019-10-28 Ashvin Nair , Shikhar Bahl , Alexander Khazatsky , Vitchyr Pong , Glen Berseth , Sergey Levine

Although deep reinforcement learning has recently been very successful at learning complex behaviors, it requires a tremendous amount of data to learn a task. One of the fundamental reasons causing this limitation lies in the nature of the…

机器人学 · 计算机科学 2022-09-19 Zhenshan Bing , Alexander Koch , Xiangtong Yao , Kai Huang , Alois Knoll

Many relevant tasks require an agent to reach a certain state, or to manipulate objects into a desired configuration. For example, we might want a robot to align and assemble a gear onto an axle or insert and turn a key in a lock. These…

人工智能 · 计算机科学 2018-07-24 Carlos Florensa , David Held , Markus Wulfmeier , Michael Zhang , Pieter Abbeel

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…

Providing a suitable reward function to reinforcement learning can be difficult in many real world applications. While inverse reinforcement learning (IRL) holds promise for automatically learning reward functions from demonstrations,…

机器学习 · 计算机科学 2019-10-29 Lantao Yu , Tianhe Yu , Chelsea Finn , Stefano Ermon

Vision-language models (VLMs) have tremendous potential for grounding language, and thus enabling language-conditioned agents (LCAs) to perform diverse tasks specified with text. This has motivated the study of LCAs based on reinforcement…

人工智能 · 计算机科学 2024-11-27 Theo Cachet , Christopher R. Dance , Olivier Sigaud

Designing rewards for Reinforcement Learning (RL) is challenging because it needs to convey the desired task, be efficient to optimize, and be easy to compute. The latter is particularly problematic when applying RL to robotics, where…

机器学习 · 计算机科学 2020-05-28 Yiming Ding , Carlos Florensa , Mariano Phielipp , Pieter Abbeel

Techniques that learn improved representations via offline data or self-supervised objectives have shown impressive results in traditional reinforcement learning (RL). Nevertheless, it is unclear how improved representation learning can…

计算与语言 · 计算机科学 2024-10-25 Vaskar Nath , Dylan Slack , Jeff Da , Yuntao Ma , Hugh Zhang , Spencer Whitehead , Sean Hendryx

Goal-conditioned reinforcement learning (RL) concerns the problem of training an agent to maximize the probability of reaching target goal states. This paper presents an analysis of the goal-conditioned setting based on optimal control. In…

机器学习 · 计算机科学 2026-05-15 Nathan P. Lawrence , Ali Mesbah

Large language models (LLMs) trained with Reinforcement Learning from Human Feedback (RLHF) have demonstrated remarkable capabilities, but their underlying reward functions and decision-making processes remain opaque. This paper introduces…

计算与语言 · 计算机科学 2025-10-07 Jared Joselowitz , Ritam Majumdar , Arjun Jagota , Matthieu Bou , Nyal Patel , Satyapriya Krishna , Sonali Parbhoo

We study the problem of learning a range of vision-based manipulation tasks from a large offline dataset of robot interaction. In order to accomplish this, humans need easy and effective ways of specifying tasks to the robot. Goal images…

机器人学 · 计算机科学 2021-11-02 Suraj Nair , Eric Mitchell , Kevin Chen , Brian Ichter , Silvio Savarese , Chelsea Finn

Reward engineering has long been a challenge in Reinforcement Learning (RL) research, as it often requires extensive human effort and iterative processes of trial-and-error to design effective reward functions. In this paper, we propose…

机器人学 · 计算机科学 2024-06-18 Yufei Wang , Zhanyi Sun , Jesse Zhang , Zhou Xian , Erdem Biyik , David Held , Zackory Erickson

Goals for reinforcement learning problems are typically defined through hand-specified rewards. To design such problems, developers of learning algorithms must inherently be aware of what the task goals are, yet we often require agents to…

机器学习 · 计算机科学 2018-03-29 Ashley D. Edwards , Laura Downs , James C. Davidson

In the real world, linguistic agents are also embodied agents: they perceive and act in the physical world. The notion of Language Grounding questions the interactions between language and embodiment: how do learning agents connect or…

机器学习 · 计算机科学 2020-06-15 Cédric Colas , Ahmed Akakzia , Pierre-Yves Oudeyer , Mohamed Chetouani , Olivier Sigaud

Reinforcement learning (RL) is a popular approach for robotic path planning in uncertain environments. However, the control policies trained for an RL agent crucially depend on user-defined, state-based reward functions. Poorly designed…

While reinforcement learning (RL) has the potential to enable robots to autonomously acquire a wide range of skills, in practice, RL usually requires manual, per-task engineering of reward functions, especially in real world settings where…

机器人学 · 计算机科学 2019-02-15 Tianhe Yu , Gleb Shevchuk , Dorsa Sadigh , Chelsea Finn
‹ 上一页 1 2 3 10 下一页 ›