Cover Image

Bigger, Regularized, Categorical: High-Capacity Value Functions are Efficient Multi-Task Learners

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Nauman, Michal, Cygan, Marek, Sferrazza, Carmelo, Kumar, Aviral, Abbeel, Pieter
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

Reward-Conditioned Reinforcement Learning
by: Nauman, Michal, et al.
Published: (2026)

Bigger, Regularized, Optimistic: scaling for compute and sample-efficient continuous control
by: Nauman, Michal, et al.
Published: (2024)

On the Theory of Risk-Aware Agents: Bridging Actor-Critic and Economics
by: Nauman, Michal, et al.
Published: (2023)

FastTD3: Simple, Fast, and Capable Reinforcement Learning for Humanoid Control
by: Seo, Younggyo, et al.
Published: (2025)

Value-Based Deep RL Scales Predictably
by: Rybkin, Oleh, et al.
Published: (2025)

Compute-Optimal Scaling for Value-Based Deep RL
by: Fu, Preston, et al.
Published: (2025)

A Case for Validation Buffer in Pessimistic Actor-Critic
by: Nauman, Michal, et al.
Published: (2024)

MaxInfoRL: Boosting exploration in reinforcement learning through information gain maximization
by: Sukhija, Bhavya, et al.
Published: (2024)

floq: Training Critics via Flow-Matching for Scaling Compute in Value-Based RL
by: Agrawalla, Bhavya, et al.
Published: (2025)

SOMBRL: Scalable and Optimistic Model-Based RL
by: Sukhija, Bhavya, et al.
Published: (2025)

HumanoidBench: Simulated Humanoid Benchmark for Whole-Body Locomotion and Manipulation
by: Sferrazza, Carmelo, et al.
Published: (2024)

Body Transformer: Leveraging Robot Embodiment for Policy Learning
by: Sferrazza, Carmelo, et al.
Published: (2024)

What Does Flow Matching Bring To TD Learning?
by: Agrawalla, Bhavya, et al.
Published: (2026)

Overestimation, Overfitting, and Plasticity in Actor-Critic: the Bitter Lesson of Reinforcement Learning
by: Nauman, Michal, et al.
Published: (2024)

Learning Sim-to-Real Humanoid Locomotion in 15 Minutes
by: Seo, Younggyo, et al.
Published: (2025)

When Does Non-Uniform Replay Matter in Reinforcement Learning?
by: Korniak, Michal, et al.
Published: (2026)

Debate2Create: Robot Co-design via Multi-Agent LLM Debate
by: Qiu, Kevin, et al.
Published: (2025)

Coarse-to-fine Q-Network with Action Sequence for Data-Efficient Reinforcement Learning
by: Seo, Younggyo, et al.
Published: (2024)

A Stable Whitening Optimizer for Efficient Neural Network Training
by: Frans, Kevin, et al.
Published: (2025)

OmniRetarget: Interaction-Preserving Data Generation for Humanoid Whole-Body Loco-Manipulation and Scene Interaction
by: Yang, Lujie, et al.
Published: (2025)

Accelerating Reinforcement Learning with Value-Conditional State Entropy Exploration
by: Kim, Dongyoung, et al.
Published: (2023)

Relative Entropy Pathwise Policy Optimization
by: Voelcker, Claas, et al.
Published: (2025)

Digi-Q: Learning Q-Value Functions for Training Device-Control Agents
by: Bai, Hao, et al.
Published: (2025)

Unsupervised Zero-Shot Reinforcement Learning via Functional Reward Encodings
by: Frans, Kevin, et al.
Published: (2024)

What Really Matters in Matrix-Whitening Optimizers?
by: Frans, Kevin, et al.
Published: (2025)

SEMDICE: Off-policy State Entropy Maximization via Stationary Distribution Correction Estimation
by: Lee, Jongmin, et al.
Published: (2025)

What Matters in Hierarchical Search for Combinatorial Reasoning Problems?
by: Zawalski, Michał, et al.
Published: (2024)

Offline Imitation Learning Through Graph Search and Retrieval
by: Yin, Zhao-Heng, et al.
Published: (2024)

Perceptive Humanoid Parkour: Chaining Dynamic Human Skills via Motion Matching
by: Wu, Zhen, et al.
Published: (2026)

Functional Graphical Models: Structure Enables Offline Data-Driven Optimization
by: Kuba, Jakub Grudzien, et al.
Published: (2024)

Vid2Sid: Videos Can Help Close the Sim2Real Gap
by: Qiu, Kevin, et al.
Published: (2026)

ActSafe: Active Exploration with Safety Constraints for Reinforcement Learning
by: As, Yarden, et al.
Published: (2024)

Is Value Learning Really the Main Bottleneck in Offline RL?
by: Park, Seohong, et al.
Published: (2024)

Steering Your Generalists: Improving Robotic Foundation Models via Value Guidance
by: Nakamoto, Mitsuhiko, et al.
Published: (2024)

DreamSmooth: Improving Model-based Reinforcement Learning via Reward Smoothing
by: Lee, Vint, et al.
Published: (2023)

Diffusion Guidance Is a Controllable Policy Improvement Operator
by: Frans, Kevin, et al.
Published: (2025)

World Model on Million-Length Video And Language With Blockwise RingAttention
by: Liu, Hao, et al.
Published: (2024)

Cliqueformer: Model-Based Optimization with Structured Transformers
by: Kuba, Jakub Grudzien, et al.
Published: (2024)

Projected Compression: Trainable Projection for Efficient Transformer Compression
by: Stefaniak, Maciej, et al.
Published: (2025)

Video2Policy: Scaling up Manipulation Tasks in Simulation through Internet Videos
by: Ye, Weirui, et al.
Published: (2025)