English
Related papers

Related papers: Cross-Entropy Games and Frost Training

200 papers

Large Language Models (LLMs) and Reinforcement Learning (RL) are two powerful approaches for building autonomous agents. However, due to limited understanding of the game environment, agents often resort to inefficient exploration and…

Machine Learning · Computer Science 2024-11-26 Ziyu Chen , Zhiqing Xiao , Xinbei Jiang , Junbo Zhao

Reinforcement Learning from Human Feedback (RLHF) or Verifiable Rewards (RLVR) are two key steps in the post-training of modern Language Models (LMs). A common problem is reward hacking, where the policy may exploit inaccuracies of the…

Machine Learning · Computer Science 2026-02-23 Johannes Ackermann , Michael Noukhovitch , Takashi Ishida , Masashi Sugiyama

Deep Reinforcement Learning has been shown to be very successful in complex games, e.g. Atari or Go. These games have clearly defined rules, and hence allow simulation. In many practical applications, however, interactions with the…

Machine Learning · Computer Science 2019-02-12 Andreas Merentitis , Kashif Rasul , Roland Vollgraf , Abdul-Saboor Sheikh , Urs Bergmann

Cross-silo federated learning (FL) is a typical FL that enables organizations(e.g., financial or medical entities) to train global models on isolated data. Reasonable incentive is key to encouraging organizations to contribute data.…

Machine Learning · Computer Science 2023-02-16 Shijing Yuan , Hongze Liu , Hongtao Lv , Zhanbo Feng , Jie Li , Hongyang Chen , Chentao Wu

Humans are masters at quickly learning many complex tasks, relying on an approximate understanding of the dynamics of their environments. In much the same way, we would like our learning agents to quickly adapt to new tasks. In this paper,…

While Large Language Models (LLMs) excel at generating human-like text, aligning their outputs with complex, qualitative goals like pedagogical soundness remains a significant challenge. Standard reinforcement learning techniques often rely…

Computation and Language · Computer Science 2025-09-17 Francesco Pappone , Ruggero Marino Lazzaroni , Federico Califano , Niccolò Gentile , Roberto Marras

The policy gradient method enjoys the simplicity of the objective where the agent optimizes the cumulative reward directly. Moreover, in the continuous action domain, parameterized distribution of action distribution allows easy control of…

Machine Learning · Computer Science 2022-12-16 Md Masudur Rahman , Yexiang Xue

Optimizing or sampling complex cost functions of combinatorial optimization problems is a longstanding challenge across disciplines and applications. When employing family of conventional algorithms based on Markov Chain Monte Carlo (MCMC)…

Machine Learning · Computer Science 2025-08-15 Dmitrii Dobrynin , Masoud Mohseni , John Paul Strachan

With the increasing pace of automation, modern robotic systems need to act in stochastic, non-stationary, partially observable environments. A range of algorithms for finding parameterized policies that optimize for long-term average…

Machine Learning · Computer Science 2019-09-04 David Nass , Boris Belousov , Jan Peters

While in general trading off exploration and exploitation in reinforcement learning is hard, under some formulations relatively simple solutions exist. In this paper, we first derive upper bounds for the utility of selecting different…

Artificial Intelligence · Computer Science 2018-06-06 Christos Dimitrakakis

Policy entropy has emerged as a fundamental measure for understanding and controlling exploration in reinforcement learning with verifiable rewards (RLVR) for LLMs. However, existing entropy-aware methods mainly regulate entropy through…

Recent advancements adopt online reinforcement learning (RL) from LLMs to text-to-image rectified flow diffusion models for reward alignment. The use of group-level rewards successfully aligns the model with the targeted reward. However, it…

Machine Learning · Computer Science 2026-01-06 Yiyang Wang , Xi Chen , Xiaogang Xu , Yu Liu , Hengshuang Zhao

What goals should a multi-goal reinforcement learning agent pursue during training in long-horizon tasks? When the desired (test time) goal distribution is too distant to offer a useful learning signal, we argue that the agent should not…

Machine Learning · Computer Science 2020-07-07 Silviu Pitis , Harris Chan , Stephen Zhao , Bradly Stadie , Jimmy Ba

We describe an iterative procedure for optimizing policies, with guaranteed monotonic improvement. By making several approximations to the theoretically-justified procedure, we develop a practical algorithm, called Trust Region Policy…

Machine Learning · Computer Science 2017-04-24 John Schulman , Sergey Levine , Philipp Moritz , Michael I. Jordan , Pieter Abbeel

Integration of reinforcement learning and imitation learning is an important problem that has been studied for a long time in the field of intelligent robotics. Reinforcement learning optimizes policies to maximize the cumulative reward,…

Machine Learning · Computer Science 2023-01-18 Akira Kinose , Tadahiro Taniguchi

In this work, we propose a novel inverse reinforcement learning (IRL) algorithm for constrained Markov decision process (CMDP) problems. In standard IRL problems, the inverse learner or agent seeks to recover the reward function of the MDP,…

Machine Learning · Computer Science 2024-01-08 Nirjhar Das , Arpan Chattopadhyay

Language models must now generalize out of the box to novel environments and work inside inference-scaling search procedures, such as AlphaEvolve, that select rollouts with a variety of task-specific reward functions. Unfortunately, the…

Temperature is a crucial hyperparameter in large language models (LLMs), controlling the trade-off between exploration and exploitation during text generation. High temperatures encourage diverse but noisy outputs, while low temperatures…

Machine Learning · Computer Science 2026-02-13 Haoran Dang , Cuiling Lan , Hai Wan , Xibin Zhao , Yan Lu

Large Reasoning Models (LRMs) have recently achieved strong mathematical and code reasoning performance through Reinforcement Learning (RL) post-training. However, we show that modern reasoning post-training induces an unintended…

Computation and Language · Computer Science 2026-05-12 Wenhui Tan , Fiorenzo Parascandolo , Enver Sangineto , Jianzhong Ju , Zhenbo Luo , Qian Cao , Rita Cucchiara , Ruihua Song , Jian Luan

Constrained reinforcement learning is to maximize the expected reward subject to constraints on utilities/costs. However, the training environment may not be the same as the test one, due to, e.g., modeling error, adversarial attack,…

Machine Learning · Computer Science 2022-09-16 Yue Wang , Fei Miao , Shaofeng Zou
‹ Prev 1 8 9 10 Next ›