# Simple Actors and Deep Critics for Scalable Reinforcement Learning

arXiv: https://arxiv.org/abs/2608.26659 · HTML: https://mlsanity.com/paper/2608.26659/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Diffusion and flow policies for robotics, one of 14 directions in Diffusion models.
- Builds on 25 of its 48 references that are in the map.
- First posted on arXiv 27 Aug 2026.

## Placed in

- Diffusion models / [Diffusion and flow policies for robotics](https://mlsanity.com/diffusion/diffusion-and-flow-policies-for-robotics/)
- Offline RL and imitation learning from data / [Offline RL algorithms](https://mlsanity.com/offlinerl/offline-rl-algorithms/)

## Builds on (most cited first, 25 of 25)

- [Gaussian Error Linear Units (GELUs)](https://mlsanity.com/paper/1606.08415/) (2016)
- [Continuous control with deep reinforcement learning](https://mlsanity.com/paper/1509.02971/) (2015)
- [OpenVLA: An Open-Source Vision-Language-Action Model](https://mlsanity.com/paper/2406.09246/) (2024)
- [Diffusion Policy: Visuomotor Policy Learning via Action Diffusion](https://mlsanity.com/paper/2303.04137/) (2023)
- [Addressing Function Approximation Error in Actor-Critic Methods](https://mlsanity.com/paper/1802.09477/) (2018)
- [π0: A Vision-Language-Action Flow Model for General Robot Control](https://mlsanity.com/paper/2410.24164/) (2024)
- [Offline Reinforcement Learning with Implicit Q-Learning](https://mlsanity.com/paper/2110.06169/) (2021)
- [A Minimalist Approach to Offline Reinforcement Learning](https://mlsanity.com/paper/2106.06860/) (2021)
- [Rainbow: Combining Improvements in Deep Reinforcement Learning](https://mlsanity.com/paper/1710.02298/) (2017)
- [AWAC: Accelerating Online Reinforcement Learning with Offline Datasets](https://mlsanity.com/paper/2006.09359/) (2020)
- [One Step Diffusion via Shortcut Models](https://mlsanity.com/paper/2410.12557/) (2024)
- [IDQL: Implicit Q-Learning as an Actor-Critic Method with Diffusion Policies](https://mlsanity.com/paper/2304.10573/) (2023)
- [Bigger, Better, Faster: Human-level Atari with human-level efficiency](https://mlsanity.com/paper/2305.19452/) (2023)
- [Stop Regressing: Training Value Functions via Classification for Scalable Deep RL](https://mlsanity.com/paper/2403.03950/) (2024)
- [Bigger, Regularized, Optimistic: scaling for compute and sample-efficient continuous control](https://mlsanity.com/paper/2405.16158/) (2024)
- [Consistency Models as a Rich and Efficient Policy Class for Reinforcement Learning](https://mlsanity.com/paper/2309.16984/) (2023)
- [Score Regularized Policy Optimization through Diffusion Behavior](https://mlsanity.com/paper/2310.07297/) (2023)
- [Improving Regression Performance with Distributional Losses](https://mlsanity.com/paper/1806.04613/) (2018)
- [1000 Layer Networks for Self-Supervised RL: Scaling Depth Can Enable New Goal-Reaching Capabilities](https://mlsanity.com/paper/2503.14858/) (2025)
- [D2RL: Deep Dense Architectures in Reinforcement Learning](https://mlsanity.com/paper/2010.09163/) (2020)
- [Boosting Continuous Control with Consistency Policy](https://mlsanity.com/paper/2310.06343/) (2023)
- [AD4RL: Autonomous Driving Benchmarks for Offline Reinforcement Learning with Value-based Dataset](https://mlsanity.com/paper/2404.02429/) (2024)
- [Multi2: Hierarchical Multi-Agent Decision-Making with LLM-Based Agents in Interactive Environments](https://mlsanity.com/paper/2606.03698/) (2026)
- [Energy-Guided Diffusion Sampling for Long-Term User Behavior Prediction in Reinforcement Learning-based Recommendation](https://mlsanity.com/paper/2510.12815/) (2025)
- [Maximum In-Support Return Modeling for Dynamic Recommendation with Language Model Prior](https://mlsanity.com/paper/2510.12816/) (2025)

## Abstract (arXiv)

Recent progress in offline reinforcement learning (RL) has been driven by expressive generative actors such as diffusion and flow-matching policies, which capture multimodal behavior in offline datasets. However, these actors require multiple denoising or integration steps per action and thus incur substantial overhead at every decision in deployment. In this work, we revisit where capacity should be invested in an offline actor--critic method. Since the critic is used only during training and is discarded at deployment while the actor runs at every decision step, allocating capacity to the critic rather than the actor is more favorable for inference-time efficiency. However, scaling MLP critics in offline RL is known to introduce several distinct instabilities that have, in practice, kept critics shallow. We identify three distinct failure modes that arise when critics are deepened in offline RL---optimization, bootstrap-noise amplification, and value-range drift---and address each with a corresponding ingredient: a residual MLP backbone, n-step bootstrap targets, and a categorical cross-entropy loss. Combining these ingredients with a lightweight deterministic actor, we propose LAC (Light Actor, deep Critic). On OGBench, LAC matches the strongest diffusion- and flow-matching baselines while achieving up to 4x lower inference latency, comparable to one-step distilled policies without distillation. Its critic recipe also transfers across actor parametrizations.