English
Related papers

Related papers: ACE : Off-Policy Actor-Critic with Causality-Aware…

200 papers

Policy gradient algorithms have driven many recent advancements in language model reasoning. An appealing property is their ability to learn from exploration on their own trajectories, a process crucial for fostering diverse and creative…

Machine Learning · Computer Science 2026-03-13 Aleksei Petrenko , Ben Lipkin , Kevin Chen , Erik Wijmans , Marco Cusumano-Towner , Raja Giryes , Philipp Krähenbühl

Simplicity is a critical inductive bias for designing data-driven controllers, especially when robustness is important. Despite the impressive results of deep reinforcement learning in complex control tasks, it is prone to capturing…

Machine Learning · Computer Science 2025-05-09 Bang You , Chenxu Wang , Huaping Liu

In this paper, we propose an actor ensemble algorithm, named ACE, for continuous control with a deterministic policy in reinforcement learning. In ACE, we use actor ensemble (i.e., multiple actors) to search the global maxima of the critic.…

Machine Learning · Computer Science 2018-11-12 Shangtong Zhang , Hao Chen , Hengshuai Yao

As a key component to intuitive cognition and reasoning solutions in human intelligence, causal knowledge provides great potential for reinforcement learning (RL) agents' interpretability towards decision-making by helping reduce the…

Machine Learning · Computer Science 2025-04-25 Ruichu Cai , Siyang Huang , Jie Qiao , Wei Chen , Yan Zeng , Keli Zhang , Fuchun Sun , Yang Yu , Zhifeng Hao

We study the problem of off-policy evaluation (OPE) in Reinforcement Learning (RL), where the aim is to estimate the performance of a new policy given historical data that may have been generated by a different policy, or policies. In…

Machine Learning · Computer Science 2019-12-16 Aurélien F. Bibaut , Ivana Malenica , Nikos Vlassis , Mark J. van der Laan

Off-policy evaluation (OPE) is a critical challenge in robust decision-making that seeks to assess the performance of a new policy using data collected under a different policy. However, the existing OPE methodologies suffer from several…

Machine Learning · Statistics 2025-02-11 Muhammad Faaiz Taufiq

Entropy-based deep reasoning has emerged as a promising direction for improving the reasoning capabilities of Large Language Models (LLMs), but existing methods often either increase response length indiscriminately or shorten responses at…

Computation and Language · Computer Science 2026-05-20 Shuyu Wei , Jian Sun , Delai Qiu , Yining Wang , Shengping Liu , Jiaen Liang , Ying Fu , Wei Huang , Jitao Sang

We consider an improper reinforcement learning setting where a learner is given $M$ base controllers for an unknown Markov decision process, and wishes to combine them optimally to produce a potentially new controller that can outperform…

Machine Learning · Computer Science 2022-07-20 Mohammadi Zaki , Avinash Mohan , Aditya Gopalan , Shie Mannor

Deep Reinforcement Learning (DRL) is widely recognized as sample-inefficient, a limitation attributable in part to the high dimensionality and substantial functional redundancy inherent to the policy parameter space. A recent framework,…

Machine Learning · Computer Science 2026-04-03 Andrea Fraschini , Davide Tenedini , Riccardo Zamboni , Mirco Mutti , Marcello Restelli

This work aims to study off-policy evaluation (OPE) under scenarios where two key reinforcement learning (RL) assumptions -- temporal stationarity and individual homogeneity are both violated. To handle the ``double inhomogeneities", we…

Methodology · Statistics 2024-08-20 Zeyu Bian , Chengchun Shi , Zhengling Qi , Lan Wang

The recent success of reinforcement learning's (RL) in solving complex tasks is most often attributed to its capacity to explore and exploit an environment where it has been trained. Sample efficiency is usually not an issue since cheap…

Computation and Language · Computer Science 2023-03-16 Govardana Sachithanandam Ramachandran , Kazuma Hashimoto , Caiming Xiong

We propose ERA, a new paradigm that constrains the sampling entropy above given thresholds by applying specially designed activations to the outputs of models. Our approach demonstrates broad effectiveness across different domains: 1) for…

Machine Learning · Computer Science 2025-10-13 Zilin Kang , Chonghua Liao , Tingqiang Xu , Huazhe Xu

Animals exhibit an innate ability to learn regularities of the world through interaction. By performing experiments in their environment, they are able to discern the causal factors of variation and infer how they affect the world's…

Machine Learning · Computer Science 2021-08-10 Sumedh A. Sontakke , Arash Mehrjou , Laurent Itti , Bernhard Schölkopf

For RL algorithms, appropriate entropy control is crucial to their effectiveness. To control the policy entropy, a commonly used method is entropy regularization, which is adopted in various popular RL algorithms including PPO, SAC and A3C.…

Machine Learning · Computer Science 2026-02-06 Han Shen

Deep reinforcement learning agents frequently suffer from premature convergence, where early entropy collapse causes the policy to discard exploratory behaviors before discovering globally optimal strategies. We introduce Optimistic Policy…

Machine Learning · Computer Science 2026-03-10 Mai Pham , Vikrant Vaze , Peter Chin

The average reward criterion is relatively less studied as most existing works in the Reinforcement Learning literature consider the discounted reward criterion. There are few recent works that present on-policy average reward actor-critic…

Machine Learning · Computer Science 2023-07-20 Naman Saxena , Subhojyoti Khastigir , Shishir Kolathaya , Shalabh Bhatnagar

Multi-agent reinforcement learning (MARL) suffers from the non-stationarity problem, which is the ever-changing targets at every iteration when multiple agents update their policies at the same time. Starting from first principle, in this…

Machine Learning · Computer Science 2022-12-05 Chuming Li , Jie Liu , Yinmin Zhang , Yuhong Wei , Yazhe Niu , Yaodong Yang , Yu Liu , Wanli Ouyang

Deep Reinforcement Learning (DRL) has achieved remarkable success, ranging from complex computer games to real-world applications, showing the potential for intelligent agents capable of learning in dynamic environments. However, its…

Robotics · Computer Science 2024-07-08 I Lee , Hoang-Giang Cao , Cong-Tinh Dao , Yu-Cheng Chen , I-Chen Wu

Deep reinforcement learning (DRL) algorithms have been demonstrated to be effective in a wide range of challenging decision making and control tasks. However, these methods typically suffer from severe action oscillations in particular in…

Machine Learning · Computer Science 2021-03-04 Chen Chen , Hongyao Tang , Jianye Hao , Wulong Liu , Zhaopeng Meng

We study how to improve large foundation vision-language-action (VLA) systems through online reinforcement learning (RL) in real-world settings. Central to this process is the value function, which provides learning signals to guide VLA…