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

arXiv: https://arxiv.org/abs/2505.23150 · HTML: https://mlsanity.com/paper/2505.23150/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- Builds on 93 of its 121 references that are in the map.
- First posted on arXiv 29 May 2025.

## Builds on (most cited first, 30 of 93)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor](https://mlsanity.com/paper/1801.01290/) (2018)
- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control](https://mlsanity.com/paper/2307.15818/) (2023)
- [Training Compute-Optimal Large Language Models](https://mlsanity.com/paper/2203.15556/) (2022)
- [OpenVLA: An Open-Source Vision-Language-Action Model](https://mlsanity.com/paper/2406.09246/) (2024)
- [Addressing Function Approximation Error in Actor-Critic Methods](https://mlsanity.com/paper/1802.09477/) (2018)
- [Asynchronous Methods for Deep Reinforcement Learning](https://mlsanity.com/paper/1602.01783/) (2016)
- [PaLM-E: An Embodied Multimodal Language Model](https://mlsanity.com/paper/2303.03378/) (2023)
- [RT-1: Robotics Transformer for Real-World Control at Scale](https://mlsanity.com/paper/2212.06817/) (2022)
- [Decision Transformer: Reinforcement Learning via Sequence Modeling](https://mlsanity.com/paper/2106.01345/) (2021)
- [Octo: An Open-Source Generalist Robot Policy](https://mlsanity.com/paper/2405.12213/) (2024)
- [Gradient Surgery for Multi-Task Learning](https://mlsanity.com/paper/2001.06782/) (2020)
- [Mastering Diverse Domains through World Models](https://mlsanity.com/paper/2301.04104/) (2023)
- [Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning](https://mlsanity.com/paper/1910.10897/) (2019)
- [Hindsight Experience Replay](https://mlsanity.com/paper/1707.01495/) (2017)
- [DeepMind Control Suite](https://mlsanity.com/paper/1801.00690/) (2018)
- [A Minimalist Approach to Offline Reinforcement Learning](https://mlsanity.com/paper/2106.06860/) (2021)
- [End-to-End Training of Deep Visuomotor Policies](https://mlsanity.com/paper/1504.00702/) (2015)
- [GradNorm: Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networks](https://mlsanity.com/paper/1711.02257/) (2017)
- [Multi-Task Learning as Multi-Objective Optimization](https://mlsanity.com/paper/1810.04650/) (2018)

## Built on by (most cited first, 23 of 23)

- [floq: Training Critics via Flow-Matching for Scaling Compute in Value-Based RL](https://mlsanity.com/paper/2509.06863/) (2025)
- [XQC: Well-conditioned Optimization Accelerates Deep Reinforcement Learning](https://mlsanity.com/paper/2509.25174/) (2025)
- [Learning Massively Multitask World Models for Continuous Control](https://mlsanity.com/paper/2511.19584/) (2025)
- [Relative Entropy Pathwise Policy Optimization](https://mlsanity.com/paper/2507.11019/) (2025)
- [Contrastive Representations for Temporal Reasoning](https://mlsanity.com/paper/2508.13113/) (2025)
- [Expressive Value Learning for Scalable Offline Reinforcement Learning](https://mlsanity.com/paper/2510.08218/) (2025)
- [FlashSAC: Fast and Stable Off-Policy Reinforcement Learning for High-Dimensional Robot Control](https://mlsanity.com/paper/2604.04539/) (2026)
- [What Makes Value Learning Efficient in Residual Reinforcement Learning?](https://mlsanity.com/paper/2602.10539/) (2026)
- [Squint: Fast Visual Reinforcement Learning for Sim-to-Real Robotics](https://mlsanity.com/paper/2602.21203/) (2026)
- [What Does Flow Matching Bring To TD Learning?](https://mlsanity.com/paper/2603.04333/) (2026)
- [EfficientTDMPC: Improved MPC Objectives for Sample-Efficient Continuous Control](https://mlsanity.com/paper/2605.16692/) (2026)
- [Scaling DRL for Decision Making: A Survey on Data, Network, and Training Budget Strategies](https://mlsanity.com/paper/2508.03194/) (2025)
- [RN-D: Discretized Categorical Actors for On-Policy Reinforcement Learning](https://mlsanity.com/paper/2601.23075/) (2026)
- [Reward-Conditioned Reinforcement Learning](https://mlsanity.com/paper/2603.05066/) (2026)
- [Debiased Model-based Representations for Sample-efficient Continuous Control](https://mlsanity.com/paper/2605.11711/) (2026)
- [Building2Building: A Large Scale Benchmark for Generalizable Real-World Reinforcement Learning](https://mlsanity.com/paper/2607.16534/) (2026)
- [Scaling Tasks, Not Samples: Mastering Humanoid Control through Multi-Task Model-Based Reinforcement Learning](https://mlsanity.com/paper/2603.01452/) (2026)
- [Low-Rank Adaptation for Critic Learning in Off-Policy Reinforcement Learning](https://mlsanity.com/paper/2604.18978/) (2026)
- [Probing the Impact of Scale on Data-Efficient, Generalist Transformer World Models for Atari](https://mlsanity.com/paper/2605.08578/) (2026)
- [When Does Non-Uniform Replay Matter in Reinforcement Learning?](https://mlsanity.com/paper/2605.10236/) (2026)
- [Representation Learning Enables Scalable Multitask Deep Reinforcement Learning](https://mlsanity.com/paper/2606.05555/) (2026)
- [V-Simba: Unleashing the Architectural Potential of RL in Visual Continuous Control](https://mlsanity.com/paper/2608.07870/) (2026)
- [Task Specialization Fine-Tuning for Contextual Reinforcement Learning](https://mlsanity.com/paper/2608.17180/) (2026)

## Abstract (arXiv)

Recent advances in language modeling and vision stem from training large models on diverse, multi-task data. This paradigm has had limited impact in value-based reinforcement learning (RL), where improvements are often driven by small models trained in a single-task context. This is because in multi-task RL sparse rewards and gradient conflicts make optimization of temporal difference brittle. Practical workflows for generalist policies therefore avoid online training, instead cloning expert trajectories or distilling collections of single-task policies into one agent. In this work, we show that the use of high-capacity value models trained via cross-entropy and conditioned on learnable task embeddings addresses the problem of task interference in online RL, allowing for robust and scalable multi-task training. We test our approach on 7 multi-task benchmarks with over 280 unique tasks, spanning high degree-of-freedom humanoid control and discrete vision-based RL. We find that, despite its simplicity, the proposed approach leads to state-of-the-art single and multi-task performance, as well as sample-efficient transfer to new tasks.