English
Related papers

Related papers: Convergence Results For Q-Learning With Experience…

200 papers

While Experience Replay - the practice of storing rollouts and reusing them multiple times during training - is a foundational technique in general RL, it remains largely unexplored in LLM post-training due to the prevailing belief that…

Machine Learning · Computer Science 2026-04-13 Charles Arnal , Vivien Cabannes , Taco Cohen , Julia Kempe , Remi Munos

A major obstacle to developing artificial intelligence applications capable of true lifelong learning is that artificial neural networks quickly or catastrophically forget previously learned tasks when trained on a new one. Numerous methods…

Machine Learning · Computer Science 2019-04-18 Gido M. van de Ven , Andreas S. Tolias

During sleep and awake rest, the hippocampus replays sequences of place cells that have been activated during prior experiences. These have been interpreted as a memory consolidation process, but recent results suggest a possible…

Artificial Intelligence · Computer Science 2018-08-14 Lise Aubin , Mehdi Khamassi , Benoît Girard

Reinforcement learning (RL) depends critically on the choice of reward functions used to capture the de- sired behavior and constraints of a robot. Usually, these are handcrafted by a expert designer and represent heuristics for relatively…

Artificial Intelligence · Computer Science 2017-03-03 Xiao Li , Cristian-Ioan Vasile , Calin Belta

Experience replay, the reuse of past data to improve sample efficiency, is ubiquitous in reinforcement learning. Though a variety of smart sampling schemes have been introduced to improve performance, uniform sampling by far remains the…

Machine Learning · Computer Science 2024-10-22 Parham Mohammad Panahi , Andrew Patterson , Martha White , Adam White

Hindsight goal relabeling has become a foundational technique in multi-goal reinforcement learning (RL). The essential idea is that any trajectory can be seen as a sub-optimal demonstration for reaching its final state. Intuitively,…

Machine Learning · Computer Science 2023-01-31 Lunjun Zhang , Bradly C. Stadie

This work extends the analysis of the theoretical results presented within the paper Is Q-Learning Provably Efficient? by Jin et al. We include a survey of related research to contextualize the need for strengthening the theoretical…

Machine Learning · Computer Science 2020-09-23 Kushagra Rastogi , Jonathan Lee , Fabrice Harel-Canada , Aditya Joglekar

We study the regret of reinforcement learning from offline data generated by a fixed behavior policy in an infinite-horizon discounted Markov decision process (MDP). While existing analyses of common approaches, such as fitted $Q$-iteration…

Machine Learning · Computer Science 2023-07-13 Yichun Hu , Nathan Kallus , Masatoshi Uehara

Hybrid Reinforcement Learning (RL), where an agent learns from both an offline dataset and online explorations in an unknown environment, has garnered significant recent interest. A crucial question posed by Xie et al. (2022) is whether…

Machine Learning · Statistics 2024-08-09 Kevin Tan , Wei Fan , Yuting Wei

Online imitation learning is the problem of how best to mimic expert demonstrations, given access to the environment or an accurate simulator. Prior work has shown that in the infinite sample regime, exact moment matching achieves value…

In Meta-Reinforcement Learning (meta-RL) an agent is trained on a set of tasks to prepare for and learn faster in new, unseen, but related tasks. The training tasks are usually hand-crafted to be representative of the expected distribution…

Artificial Intelligence · Computer Science 2021-07-07 Ricardo Luna Gutierrez , Matteo Leonetti

The inverse reinforcement learning approach to imitation learning is a double-edged sword. On the one hand, it can enable learning from a smaller number of expert demonstrations with more robustness to error compounding than behavioral…

Machine Learning · Computer Science 2024-06-06 Juntao Ren , Gokul Swamy , Zhiwei Steven Wu , J. Andrew Bagnell , Sanjiban Choudhury

It has previously been shown that by using reinforcement learning (RL), agents can derive simple approximate and exact-restricted numeral systems that are similar to human ones (Carlsson, 2021). However, it is a major challenge to show how…

Computation and Language · Computer Science 2025-05-20 Andrea Silvi , Jonathan Thomas , Emil Carlsson , Devdatt Dubhashi , Moa Johansson

Reinforcement learning with verifiable rewards (RLVR) plays a crucial role in expanding the capacities of LLM reasoning, but GRPO-style training is dominated by expensive rollouts and wastes compute on unusable prompts. We propose Prompt…

Machine Learning · Computer Science 2026-03-24 Andrei Baroian , Rutger Berger

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,…

Machine Learning · Computer Science 2019-10-29 Lantao Yu , Tianhe Yu , Chelsea Finn , Stefano Ermon

Online Reinforcement Learning (RL) is typically framed as the process of minimizing cumulative regret (CR) through interactions with an unknown environment. However, real-world RL applications usually involve a sequence of tasks, and the…

Machine Learning · Statistics 2024-10-28 Ziping Xu , Kelly W. Zhang , Susan A. Murphy

Recently, several authors have advocated the use of rule learning algorithms to model multi-label data, as rules are interpretable and can be comprehended, analyzed, or qualitatively evaluated by domain experts. Many rule learning…

Machine Learning · Computer Science 2020-12-09 Michael Rapp , Eneldo Loza Mencía , Johannes Fürnkranz

Reinforcement learning (RL) has traditionally been understood from an episodic perspective; the concept of non-episodic RL, where there is no restart and therefore no reliable recovery, remains elusive. A fundamental question in…

Machine Learning · Computer Science 2021-05-31 Shuang Liu , Hao Su

After the recent groundbreaking results of AlphaGo, we have seen a strong interest in reinforcement learning in game playing. General Game Playing (GGP) provides a good testbed for reinforcement learning. In GGP, a specification of games…

Artificial Intelligence · Computer Science 2018-05-22 Hui Wang , Michael Emmerich , Aske Plaat

Rehearsal-based methods have shown superior performance in addressing catastrophic forgetting in continual learning (CL) by storing and training on a subset of past data alongside new data in current task. While such a concurrent rehearsal…

Machine Learning · Computer Science 2025-06-03 Junze Deng , Qinhang Wu , Peizhong Ju , Sen Lin , Yingbin Liang , Ness Shroff