English
Related papers

Related papers: Revisit Policy Optimization in Matrix Form

200 papers

We study the problem of model-free reinforcement learning, which is often solved following the principle of Generalized Policy Iteration (GPI). While GPI is typically an interplay between policy evaluation and policy improvement, most…

Machine Learning · Computer Science 2023-02-28 Changnan Xiao , Haosen Shi , Jiajun Fan , Shihong Deng , Haiyan Yin

We consider the problem of offline reinforcement learning with model-based control, whose goal is to learn a dynamics model from the experience replay and obtain a pessimism-oriented agent under the learned model. Current model-based…

Machine Learning · Computer Science 2021-09-16 Ruizhen Liu , Dazhi Zhong , Zhicong Chen

Reinforcement learning with verifiable rewards (RLVR), due to the deterministic verification, becomes a dominant paradigm for enhancing the reasoning ability of large language models (LLMs). The community witnesses the rapid change from the…

Computation and Language · Computer Science 2026-05-08 Mingwei Xu , Hao Fang

Reinforcement learning means finding the optimal course of action in Markovian environments without knowledge of the environment's dynamics. Stochastic optimization algorithms used in the field rely on estimates of the value of a policy.…

Machine Learning · Computer Science 2017-05-25 Leonid Peshkin , Sayan Mukherjee

This study proposes a regime-aware reinforcement learning framework for long-horizon portfolio optimization. Moving beyond traditional feedforward and GARCH-based models, we design realistic environments where agents dynamically reallocate…

Portfolio Management · Quantitative Finance 2025-09-19 Gabriel Nixon Raj

This paper considers the problem of learning safe policies in the context of reinforcement learning (RL). In particular, we consider the notion of probabilistic safety. This is, we aim to design policies that maintain the state of the…

Machine Learning · Computer Science 2023-04-20 Weiqin Chen , Dharmashankar Subramanian , Santiago Paternain

Traditional model-based reinforcement learning approaches learn a model of the environment dynamics without explicitly considering how it will be used by the agent. In the presence of misspecified model classes, this can lead to poor…

Machine Learning · Computer Science 2020-10-20 Pierluca D'Oro , Alberto Maria Metelli , Andrea Tirinzoni , Matteo Papini , Marcello Restelli

Reinforcement Learning, particularly through policy gradient methods, has played a central role in enabling reasoning capabilities of Large Language Models. However, the optimization stability of policy gradients in this setting remains…

Machine Learning · Computer Science 2026-03-03 Luckeciano C. Melo , Alessandro Abate , Yarin Gal

On-policy deep reinforcement learning algorithms have low data utilization and require significant experience for policy improvement. This paper proposes a proximal policy optimization algorithm with prioritized trajectory replay (PTR-PPO)…

Machine Learning · Computer Science 2021-12-09 Xingxing Liang , Yang Ma , Yanghe Feng , Zhong Liu

Experience replay enables reinforcement learning agents to memorize and reuse past experiences, just as humans replay memories for the situation at hand. Contemporary off-policy algorithms either replay past experiences uniformly or utilize…

Machine Learning · Computer Science 2019-06-21 Daochen Zha , Kwei-Herng Lai , Kaixiong Zhou , Xia Hu

Existing LLM-based policy optimizers see only scalar rewards: that a policy scored 0.45, but not whether the agent got stuck in a loop, fell into a hole on the third step, or performed well on 19 out of 20 rollouts and failed…

Machine Learning · Computer Science 2026-05-12 Rahaf Abu Hara , Vaibbhav Murarri , Claudio Zito

We argue that decomposing reward into weighted, verifiable criteria and using an LLM judge to score them provides a partial-credit optimization signal: instead of a binary outcome or a single holistic score, each response is graded along…

Artificial Intelligence · Computer Science 2026-05-11 Manish Bhattarai , Ismael Boureima , Nishath Rajiv Ranasinghe , Scott Pakin , Dan O'Malley

Task-specific scores are often used to optimize for and evaluate the performance of conditional text generation systems. However, such scores are non-differentiable and cannot be used in the standard supervised learning paradigm. Hence,…

Machine Learning · Computer Science 2019-09-10 James O' Neill , Danushka Bollegala

In continuing tasks, average-reward reinforcement learning may be a more appropriate problem formulation than the more common discounted reward formulation. As usual, learning an optimal policy in this setting typically requires a large…

Artificial Intelligence · Computer Science 2023-01-18 Yuqian Jiang , Sudarshanan Bharadwaj , Bo Wu , Rishi Shah , Ufuk Topcu , Peter Stone

Scaling reinforcement learning to tens of thousands of parallel environments requires overcoming the limited exploration capacity of a single policy. Ensemble-based policy gradient methods, which employ multiple policies to collect diverse…

Machine Learning · Computer Science 2026-03-04 Naoki Shitanda , Motoki Omura , Tatsuya Harada , Takayuki Osa

We develop a normative framework for hierarchical model-based policy optimization based on applying second-order methods in the space of all possible state-action paths. The resulting natural path gradient performs policy updates in a…

Machine Learning · Computer Science 2020-01-03 Daniel McNamee

Differentiable reinforcement learning (RL) frameworks like DiffRO offer a powerful approach for controllable text-to-speech (TTS), but are vulnerable to reward hacking, particularly for nuanced tasks like emotion control. The policy model…

Sound · Computer Science 2026-02-17 Cong Wang , Changfeng Gao , Yang Xiang , Zhihao Du , Keyu An , Han Zhao , Qian Chen , Xiangang Li , Yingming Gao , Ya Li

Policy optimization methods are popular reinforcement learning algorithms in practice. Recent works have built theoretical foundation for them by proving $\sqrt{T}$ regret bounds even when the losses are adversarial. Such bounds are tight…

Machine Learning · Computer Science 2023-02-21 Christoph Dann , Chen-Yu Wei , Julian Zimmert

Policy optimization is a widely-used method in reinforcement learning. Due to its local-search nature, however, theoretical guarantees on global optimality often rely on extra assumptions on the Markov Decision Processes (MDPs) that bypass…

Machine Learning · Computer Science 2021-07-20 Haipeng Luo , Chen-Yu Wei , Chung-Wei Lee

In deep reinforcement learning, policy optimization methods need to deal with issues such as function approximation and the reuse of off-policy data. Standard policy gradient methods do not handle off-policy data well, leading to premature…

Machine Learning · Computer Science 2025-01-28 Qing Wang , Yingru Li , Jiechao Xiong , Tong Zhang
‹ Prev 1 3 4 5 6 7 10 Next ›