2023-12-01 更新
Reinforcement Replaces Supervision: Query focused Summarization using Deep Reinforcement Learning
Authors:Swaroop Nath, Harshad Khadilkar, Pushpak Bhattacharyya
Query-focused Summarization (QfS) deals with systems that generate summaries from document(s) based on a query. Motivated by the insight that Reinforcement Learning (RL) provides a generalization to Supervised Learning (SL) for Natural Language Generation, and thereby performs better (empirically) than SL, we use an RL-based approach for this task of QfS. Additionally, we also resolve the conflict of employing RL in Transformers with Teacher Forcing. We develop multiple Policy Gradient networks, trained on various reward signals: ROUGE, BLEU, and Semantic Similarity, which lead to a 10-point improvement over the State-of-the-Art approach on the ROUGE-L metric for a benchmark dataset (ELI5). We also show performance of our approach in zero-shot setting for another benchmark dataset (DebatePedia) — our approach leads to results comparable to baselines, which were specifically trained on DebatePedia. To aid the RL training, we propose a better semantic similarity reward, enabled by a novel Passage Embedding scheme developed using Cluster Hypothesis. Lastly, we contribute a gold-standard test dataset to further research in QfS and Long-form Question Answering (LfQA).
PDF
点此查看论文截图
Bias Resilient Multi-Step Off-Policy Goal-Conditioned Reinforcement Learning
Authors:Lisheng Wu, Ke Chen
In goal-conditioned reinforcement learning (GCRL), sparse rewards present significant challenges, often obstructing efficient learning. Although multi-step GCRL can boost this efficiency, it can also lead to off-policy biases in target values. This paper dives deep into these biases, categorizing them into two distinct categories: “shooting” and “shifting”. Recognizing that certain behavior policies can hasten policy refinement, we present solutions designed to capitalize on the positive aspects of these biases while minimizing their drawbacks, enabling the use of larger step sizes to speed up GCRL. An empirical study demonstrates that our approach ensures a resilient and robust improvement, even in ten-step learning scenarios, leading to superior learning efficiency and performance that generally surpass the baseline and several state-of-the-art multi-step GCRL benchmarks.
PDF 26 pages, 7 figures
点此查看论文截图
SCOPE-RL: A Python Library for Offline Reinforcement Learning and Off-Policy Evaluation
Authors:Haruka Kiyohara, Ren Kishimoto, Kosuke Kawakami, Ken Kobayashi, Kazuhide Nakata, Yuta Saito
This paper introduces SCOPE-RL, a comprehensive open-source Python software designed for offline reinforcement learning (offline RL), off-policy evaluation (OPE), and selection (OPS). Unlike most existing libraries that focus solely on either policy learning or evaluation, SCOPE-RL seamlessly integrates these two key aspects, facilitating flexible and complete implementations of both offline RL and OPE processes. SCOPE-RL put particular emphasis on its OPE modules, offering a range of OPE estimators and robust evaluation-of-OPE protocols. This approach enables more in-depth and reliable OPE compared to other packages. For instance, SCOPE-RL enhances OPE by estimating the entire reward distribution under a policy rather than its mere point-wise expected value. Additionally, SCOPE-RL provides a more thorough evaluation-of-OPE by presenting the risk-return tradeoff in OPE results, extending beyond mere accuracy evaluations in existing OPE literature. SCOPE-RL is designed with user accessibility in mind. Its user-friendly APIs, comprehensive documentation, and a variety of easy-to-follow examples assist researchers and practitioners in efficiently implementing and experimenting with various offline RL methods and OPE estimators, tailored to their specific problem contexts. The documentation of SCOPE-RL is available at https://scope-rl.readthedocs.io/en/latest/.
PDF preprint, open-source software: https://github.com/hakuhodo-technologies/scope-rl
点此查看论文截图
LMRL Gym: Benchmarks for Multi-Turn Reinforcement Learning with Language Models
Authors:Marwa Abdulhai, Isadora White, Charlie Snell, Charles Sun, Joey Hong, Yuexiang Zhai, Kelvin Xu, Sergey Levine
Large language models (LLMs) provide excellent text-generation capabilities, but standard prompting and generation methods generally do not lead to intentional or goal-directed agents and might necessitate considerable prompt tuning. This becomes particularly apparent in multi-turn conversations: even the best current LLMs rarely ask clarifying questions, engage in explicit information gathering, or take actions now that lead to better decisions after multiple turns. Reinforcement learning has the potential to leverage the powerful modeling capabilities of LLMs, as well as their internal representation of textual interactions, to create capable goal-directed language agents. This can enable intentional and temporally extended interactions, such as with humans, through coordinated persuasion and carefully crafted questions, or in goal-directed play through text games to bring about desired final outcomes. However, enabling this requires the community to develop stable and reliable reinforcement learning algorithms that can effectively train LLMs. Developing such algorithms requires tasks that can gauge progress on algorithm design, provide accessible and reproducible evaluations for multi-turn interactions, and cover a range of task properties and challenges in improving reinforcement learning algorithms. Our paper introduces the LMRL-Gym benchmark for evaluating multi-turn RL for LLMs, together with an open-source research framework containing a basic toolkit for getting started on multi-turn RL with offline value-based and policy-based RL methods. Our benchmark consists of 8 different language tasks, which require multiple rounds of language interaction and cover a range of tasks in open-ended dialogue and text games.
PDF
点此查看论文截图
Handling Cost and Constraints with Off-Policy Deep Reinforcement Learning
Authors:Jared Markowitz, Jesse Silverberg, Gary Collins
By reusing data throughout training, off-policy deep reinforcement learning algorithms offer improved sample efficiency relative to on-policy approaches. For continuous action spaces, the most popular methods for off-policy learning include policy improvement steps where a learned state-action ($Q$) value function is maximized over selected batches of data. These updates are often paired with regularization to combat associated overestimation of $Q$ values. With an eye toward safety, we revisit this strategy in environments with “mixed-sign” reward functions; that is, with reward functions that include independent positive (incentive) and negative (cost) terms. This setting is common in real-world applications, and may be addressed with or without constraints on the cost terms. We find the combination of function approximation and a term that maximizes $Q$ in the policy update to be problematic in such environments, because systematic errors in value estimation impact the contributions from the competing terms asymmetrically. This results in overemphasis of either incentives or costs and may severely limit learning. We explore two remedies to this issue. First, consistent with prior work, we find that periodic resetting of $Q$ and policy networks can be used to reduce value estimation error and improve learning in this setting. Second, we formulate novel off-policy actor-critic methods for both unconstrained and constrained learning that do not explicitly maximize $Q$ in the policy update. We find that this second approach, when applied to continuous action spaces with mixed-sign rewards, consistently and significantly outperforms state-of-the-art methods augmented by resetting. We further find that our approach produces agents that are both competitive with popular methods overall and more reliably competent on frequently-studied control problems that do not have mixed-sign rewards.
PDF 22 pages, 16 figures
点此查看论文截图