arXiv Machine Learning
Streaming Deep Reinforcement Learning Finally Works
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv AI
Oct 31
Towards Batch-to-Streaming Deep Reinforcement Learning for Continuous Control
The paper introduces two new streaming deep reinforcement learning algorithms—Streaming Soft Actor-Critic (S2AC) and Streaming Deterministic Actor-Critic (SDAC)—designed to work with state‑of‑the‑art batch RL methods and suitable for on‑device fine‑tuning, such as Sim2Real transfer. These algorithms achieve performance comparable to existing streaming baselines on standard benchmarks without the need for extensive per‑environment hyperparameter tuning. The authors also examine the challenges of transitioning from batch to streaming RL, demonstrating that a naive approach can degrade pre‑trained policy performance and propose a principled solution to mitigate this issue.
arXiv Machine Learning
Aug 11
V-Simba: Unleashing the Architectural Potential of RL in Visual Continuous Control
arXiv:2608. 07870v1 Announce Type: new Abstract: Improving sample efficiency remains a core challenge in reinforcement learning (RL), especially in real-world settings like robotics, where data collection is costly.
arXiv Machine Learning
Sep 17
Reinforcement Learning for Real-Time Vision-Language-Action Policies
The paper presents Real‑Time EXPO‑FT, a reinforcement learning framework that fine‑tunes large Vision‑Language‑Action models for real‑time robotic control. It separates slow, expressive action generation from fast, reactive edits, allowing a lightweight policy to adjust actions based on the latest observation. Experiments on the Kinetix benchmark and four dynamic real‑world tasks show that Real‑Time EXPO‑FT achieves superior performance, improving policy success rates from 42% to 97% with only ten minutes of online data and no human intervention.
arXiv Machine Learning
Jun 19
Approximate Next Policy Sampling: Replacing Conservative Target Policy Updates in Deep RL
arXiv:2605. 05481v2 Announce Type: replace Abstract: We revisit a classic "chicken-and-egg" problem in reinforcement learning: to safely improve a policy, the value function must be accurate on the state-visitation distribution of the updated policy.
arXiv AI
Oct 27
Streaming Recurrent Memory
arXiv:2610.34833v1 Announce Type: cross Abstract: Natural intelligence learns from a continuous stream of sensorimotor experience: data can arrive at high bandwidth, and behavior adapts to feedback a...
arXiv AI
Sep 30
KV-streams for Efficient Compaction in Agentic Reinforcement Learning
arXiv:2609.35750v2 Announce Type: replace-cross Abstract: Scaling the horizon of agentic LLMs is bottlenecked by the need to fit ever longer context traces in GPU memory. Context compaction has been...