Hugging Face Trending Papers July 2, 2026

Learning the Supports for Categorical Critic in Reinforcement Learning

Read the original on Hugging Face Trending Papers →

Value functions are an essential component in actor-critic based deep reinforcement learning (RL). Conventionally, these functions are trained as a regression task by minimising the mean squared error (MSE) relative to bootstrapped target values.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at Hugging Face Trending Papers.

reinforcement-learning

arXiv Machine Learning

Jul 3

Learning the Supports for Categorical Critic in Reinforcement Learning

arXiv:2607. 01880v1 Announce Type: new Abstract: Value functions are an essential component in actor-critic based deep reinforcement learning (RL).

By Jen-Yen Chang, Takayuki Osa, Tatsuya Harada

reinforcement-learning

arXiv Machine Learning

Jul 30

Collaborative Weighting with Pessimistic Critic for Mitigating Overestimation in Off-Policy Reinforcement Learning

arXiv:2607. 26509v1 Announce Type: new Abstract: Deep off-policy reinforcement learning algorithms for continuous control typically rely on neural value function approximation to guide policy improvement.

By Gong Gao, Xiao Lai, Ziqi Xie, Guojie Chen, Xianhui Liu, Weidong Zhao

reinforcement-learning safety

arXiv Machine Learning

Jun 25

RN-D: Discretized Categorical Actors for On-Policy Reinforcement Learning

arXiv:2601. 23075v2 Announce Type: replace Abstract: On-policy Reinforcement Learning (RL) remains a dominant paradigm for continuous control, yet standard implementations rely on Gaussian actors and relatively shallow MLP policies, often leading to brittle optimization when gradients are noisy, and policy updates must be conservative.

By Yuexin Bian, Jie Feng, Tao Wang, Yijiang Li, Sicun Gao, Yuanyuan Shi

reinforcement-learning benchmarks

arXiv Machine Learning

Aug 4

Start Classifying: Categorical Critics for LLM Reinforcement Learning

arXiv:2608. 02181v1 Announce Type: new Abstract: Proximal Policy Optimization (PPO) for large language models typically trains its critic by mean-squared-error (MSE) regression on scalar value targets.

By Zhijian Zhou, Long Li, Xuan Zhang, Zongkai Liu, Yulei Qin, Ke Li, Xing Sun, Xiaoyu Tan, Chao Qu, Yuan Qi

llms reinforcement-learning

arXiv Machine Learning

Aug 24

Decoupling Policy Extraction for Offline Reinforcement Learning

arXiv:2608.20909v1 Announce Type: new Abstract: Offline RL methods commonly jointly train the actor and critic, where the critic is used to guide the actor toward higher-value actions. This coupled l...

By Xuyao Lin, Yixiang Shan, Jinru Duan, Tao Yang, Xinyu Zhao, Runyu Lei, Yiming Zhao, Jiaxin Fan, Zongbao Feng, Peng Jia

rag reinforcement-learning

Hugging Face Trending Papers

Sep 23

Limiting-Kernel Q($λ$): Bridging Short and Long Horizons

In value-based reinforcement learning, improving the accuracy of policy evaluation has been shown to improve downstream policy optimization performance. The widely adopted family of approximations rel...

reinforcement-learning benchmarks

One email a morning, machine-written

Related stories

Learning the Supports for Categorical Critic in Reinforcement Learning

Collaborative Weighting with Pessimistic Critic for Mitigating Overestimation in Off-Policy Reinforcement Learning

RN-D: Discretized Categorical Actors for On-Policy Reinforcement Learning

Start Classifying: Categorical Critics for LLM Reinforcement Learning

Decoupling Policy Extraction for Offline Reinforcement Learning

Limiting-Kernel Q($λ$): Bridging Short and Long Horizons