English
Related papers

Related papers: ETHER: Aligning Emergent Communication for Hindsig…

200 papers

Reinforcement learning has seen wide success in finetuning large language models to better align with instructions via human feedback. The so-called algorithm, Reinforcement Learning with Human Feedback (RLHF) demonstrates impressive…

Computation and Language · Computer Science 2023-02-13 Tianjun Zhang , Fangchen Liu , Justin Wong , Pieter Abbeel , Joseph E. Gonzalez

This paper introduces ACS2HER, a novel integration of the Anticipatory Classifier System (ACS2) with the Hindsight Experience Replay (HER) mechanism. While ACS2 is highly effective at building cognitive maps through latent learning, its…

Machine Learning · Computer Science 2026-01-15 Olgierd Unold , Stanisław Franczyk

Exploration in environments with sparse feedback remains a challenging research problem in reinforcement learning (RL). When the RL agent explores the environment randomly, it results in low exploration efficiency, especially in robotic…

Robotics · Computer Science 2020-11-19 Boyao Li , Tao Lu , Jiayi Li , Ning Lu , Yinghao Cai , Shuo Wang

Goal-oriented reinforcement learning has recently been a practical framework for robotic manipulation tasks, in which an agent is required to reach a certain goal defined by a function on the state space. However, the sparsity of such…

Machine Learning · Computer Science 2019-12-19 Zhizhou Ren , Kefan Dong , Yuan Zhou , Qiang Liu , Jian Peng

Hindsight experience replay (HER) is a goal relabelling technique typically used with off-policy deep reinforcement learning algorithms to solve goal-oriented tasks; it is well suited to robotic manipulation tasks that deliver only sparse…

Machine Learning · Computer Science 2021-11-10 Tianhong Dai , Hengyan Liu , Kai Arulkumaran , Guangyu Ren , Anil Anthony Bharath

Training LLMs as interactive agents for multi-turn decision-making remains challenging, particularly in long-horizon tasks with sparse and delayed rewards, where agents must execute extended sequences of actions before receiving meaningful…

Machine Learning · Computer Science 2026-05-12 Jiangweizhi Peng , Yuanxin Liu , Ruida Zhou , Charles Fleming , Zhaoran Wang , Alfredo Garcia , Mingyi Hong

Reinforcement learning methods have been used for learning dialogue policies. However, learning an effective dialogue policy frequently requires prohibitively many conversations. This is partly because of the sparse rewards in dialogues,…

Artificial Intelligence · Computer Science 2018-11-26 Keting Lu , Shiqi Zhang , Xiaoping Chen

To build agents that can collaborate effectively with others, recent research has trained artificial agents to communicate with each other in Lewis-style referential games. However, this often leads to successful but uninterpretable…

Computation and Language · Computer Science 2022-01-11 Jesse Mu , Noah Goodman

Hindsight experience replay (HER) accelerates off-policy reinforcement learning algorithms for environments that emit sparse rewards by modifying the goal of the episode post-hoc to be some state achieved during the episode. Because…

Machine Learning · Computer Science 2024-10-31 Douglas C. Crowder , Darrien M. McKenzie , Matthew L. Trappett , Frances S. Chance

Even though reinforcement-learning-based algorithms achieved superhuman performance in many domains, the field of robotics poses significant challenges as the state and action spaces are continuous, and the reward function is predominantly…

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…

Machine Learning · Computer Science 2020-05-28 Yiming Ding , Carlos Florensa , Mariano Phielipp , Pieter Abbeel

Providing Reinforcement Learning (RL) agents with human feedback can dramatically improve various aspects of learning. However, previous methods require human observer to give inputs explicitly (e.g., press buttons, voice interface),…

Neural and Evolutionary Computing · Computer Science 2020-10-15 Duo Xu , Mohit Agarwal , Ekansh Gupta , Faramarz Fekri , Raghupathy Sivakumar

Solving multi-goal reinforcement learning (RL) problems with sparse rewards is generally challenging. Existing approaches have utilized goal relabeling on collected experiences to alleviate issues raised from sparse rewards. However, these…

Machine Learning · Computer Science 2021-11-30 Rui Yang , Meng Fang , Lei Han , Yali Du , Feng Luo , Xiu Li

Reinforcement Learning (RL) has shown promise for aligning Large Language Models (LLMs) to follow instructions with various constraints. Despite the encouraging results, RL improvement inevitably relies on sampling successful, high-quality…

Artificial Intelligence · Computer Science 2025-12-30 Kongcheng Zhang , Qi Yao , Shunyu Liu , Wenjian Zhang , Min Cen , Yang Zhou , Wenkai Fang , Yiru Zhao , Baisheng Lai , Mingli Song

Large language model (LLM) agents have been applied to sequential decision-making tasks such as web navigation, but without any environment-specific experiences, they often fail in these complex tasks. Moreover, current LLM agents are not…

Artificial Intelligence · Computer Science 2025-06-10 Yitao Liu , Chenglei Si , Karthik Narasimhan , Shunyu Yao

First-order relational languages have been used in MDP planning and reinforcement learning (RL) for two main purposes: specifying MDPs in compact form, and representing and learning policies that are general and not tied to specific…

Artificial Intelligence · Computer Science 2025-12-23 Simon Ståhlberg , Hector Geffner

There is renewed interest in simulating language emergence among deep neural agents that communicate to jointly solve a task, spurred by the practical aim to develop language-enabled interactive AIs, as well as by theoretical questions…

Computation and Language · Computer Science 2019-10-15 Eugene Kharitonov , Rahma Chaabouni , Diane Bouchacourt , Marco Baroni

Emergent Language (EL) focuses on the emergence of communication among artificial agents. Although symbolic communication channels more closely mirror the discrete nature of human language, learning such protocols remains fundamentally…

Computation and Language · Computer Science 2026-02-24 Mohammad Mahdi Samiei Paqaleh , Mehdi Jamalkhah , Mahdieh Soleymani Baghshah

Referential games offer a grounded learning environment for neural agents which accounts for the fact that language is functionally used to communicate. However, they do not take into account a second constraint considered to be fundamental…

Computation and Language · Computer Science 2021-02-02 Gautier Dagan , Dieuwke Hupkes , Elia Bruni

Actor learning and critic learning are two components of the outstanding and mostly used Deep Deterministic Policy Gradient (DDPG) reinforcement learning method. Since actor and critic learning plays a significant role in the overall…

Robotics · Computer Science 2022-10-25 Adarsh Sehgal , Muskan Sehgal , Hung Manh La