Imitate Optimal Policy: Prevail and Induce Action Collapse in Policy Gradient

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhou, Zhongzhu, Yang, Yibo, Chen, Ziyan, Bie, Fengxiang, Xia, Haojun, Wu, Xiaoxia, Wu, Robert, Athiwaratkun, Ben, Ghanem, Bernard, Song, Shuaiwen Leon
Format:	Preprint
Published:	2025
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

CARE: Covariance-Aware and Rank-Enhanced Decomposition for Enabling Multi-Head Latent Attention
by: Zhou, Zhongzhu, et al.
Published: (2026)

OSCAR: Offline Spectral Covariance-Aware Rotation for 2-bit KV Cache Quantization
by: Zhou, Zhongzhu, et al.
Published: (2026)

CorDA: Context-Oriented Decomposition Adaptation of Large Language Models for Task-Aware Parameter-Efficient Fine-tuning
by: Yang, Yibo, et al.
Published: (2024)

Understanding and Steering the Cognitive Behaviors of Reasoning Models at Test-Time
by: Zhang, Zhenyu, et al.
Published: (2025)

Kitty: Accurate and Efficient 2-bit KV Cache Quantization with Dynamic Channel-wise Precision Boost
by: Xia, Haojun, et al.
Published: (2025)

When RL Meets Adaptive Speculative Training: A Unified Training-Serving System
by: Wang, Junxiong, et al.
Published: (2026)

SAW-INT4: System-Aware 4-Bit KV-Cache Quantization for Real-World LLM Serving
by: Jia, Jinda, et al.
Published: (2026)

Data Diversification Methods In Alignment Enhance Math Performance In LLMs
by: Dokmeci, Berkan, et al.
Published: (2025)

Introspective Diffusion Language Models
by: Yu, Yifan, et al.
Published: (2026)

FP6-LLM: Efficiently Serving Large Language Models Through FP6-Centric Algorithm-System Co-Design
by: Xia, Haojun, et al.
Published: (2024)

Ladder-residual: parallelism-aware architecture for accelerating large model inference with communication overlapping
by: Zhang, Muru, et al.
Published: (2025)

Dragonfly: Multi-Resolution Zoom-In Encoding Enhances Vision-Language Models
by: Thapa, Rahul, et al.
Published: (2024)

Off-OAB: Off-Policy Policy Gradient Method with Optimal Action-Dependent Baseline
by: Meng, Wenjia, et al.
Published: (2024)

Think Deep, Think Fast: Investigating Efficiency of Verifier-free Inference-time-scaling Methods
by: Wang, Junlin, et al.
Published: (2025)

Improving Model Alignment Through Collective Intelligence of Open-Source LLMS
by: Wang, Junlin, et al.
Published: (2025)

How Well Can General Vision-Language Models Learn Medicine By Watching Public Educational Videos?
by: Thapa, Rahul, et al.
Published: (2025)

English‐Only Policies and Allegations of Racism in Nursing: Safety, Culture and Respect Prevail
by: Sharon Brownie, et al.
Published: (2025)

Learning Optimal Deterministic Policies with Stochastic Policy Gradients
by: Montenegro, Alessandro, et al.
Published: (2024)

Purifying Task Vectors in Knowledge-Aware Subspace for Model Merging
by: An, Bang, et al.
Published: (2025)

Is Your Imitation Learning Policy Better than Mine? Policy Comparison with Near-Optimal Stopping
by: Snyder, David, et al.
Published: (2025)

Disentangling Reasoning and Knowledge in Medical Large Language Models
by: Thapa, Rahul, et al.
Published: (2025)

GoTTA be Diverse: Rethinking Memory Policies for Test-Time Adaptation
by: Alhuwaider, Shyma, et al.
Published: (2026)

Towards Interpretable Deep Local Learning with Successive Gradient Reconciliation
by: Yang, Yibo, et al.
Published: (2024)

Video Self-Stitching Graph Network for Temporal Action Localization
by: Zhao, Chen, et al.
Published: (2020)

Geometry-aware Policy Imitation
by: Li, Yiming, et al.
Published: (2025)

Policy Gradients for Optimal Parallel Tempering MCMC
by: Zhao, Daniel, et al.
Published: (2024)

HiPolicy: Hierarchical Multi-Frequency Action Chunking for Policy Learning
by: Zhang, Jiyao, et al.
Published: (2026)

Policy Gradient Converges to the Globally Optimal Policy for Nearly Linear-Quadratic Regulators
by: Han, Yinbin, et al.
Published: (2023)

GFlowNet Training by Policy Gradients
by: Niu, Puhua, et al.
Published: (2024)

CoLA-Flow Policy: Temporally Coherent Imitation Learning via Continuous Latent Action Flow Matching for Robotic Manipulation
by: Songwei, Wu, et al.
Published: (2026)

Human-assisted Robotic Policy Refinement via Action Preference Optimization
by: Xia, Wenke, et al.
Published: (2025)

Globally Stable Neural Imitation Policies
by: Abyaneh, Amin, et al.
Published: (2024)

Understanding and Preventing Entropy Collapse in RLVR with On-Policy Entropy Flow Optimization
by: Xu, Huimin, et al.
Published: (2026)

Performative Policy Gradient: Optimality in Performative Reinforcement Learning
by: Basu, Debabrota, et al.
Published: (2025)

Overcoming Valid Action Suppression in Unmasked Policy Gradient Algorithms
by: Zabounidis, Renos, et al.
Published: (2026)

FlowPG: Action-constrained Policy Gradient with Normalizing Flows
by: Brahmanage, Janaka Chathuranga, et al.
Published: (2024)

Zero Collapse: A Failure Mode of Policy Gradient Methods in Discontinuous Reward Environments
by: Kumar, Nishant, et al.
Published: (2026)

AED: Adaptable Error Detection for Few-shot Imitation Policy
by: Yeh, Jia-Fong, et al.
Published: (2024)

Uncertainty-Aware Deployment of Pre-trained Language-Conditioned Imitation Learning Policies
by: Wu, Bo, et al.
Published: (2024)

Where-to-Learn: Analytical Policy Gradient Directed Exploration for On-Policy Robotic Reinforcement Learning
by: Chang, Leixin, et al.
Published: (2026)