# Streetwise Agents: Empowering Offline RL Policies to Outsmart Exogenous Stochastic Disturbances in RTC

arXiv: https://arxiv.org/abs/2411.06815 · HTML: https://mlsanity.com/paper/2411.06815/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Offline multi-agent RL, one of 13 directions in Offline RL and imitation learning from data.
- Builds on 11 of its 58 references that are in the map.
- First posted on arXiv 11 Nov 2024.

## Placed in

- Offline RL and imitation learning from data / [Offline multi-agent RL](https://mlsanity.com/offlinerl/offline-multi-agent-rl/)

## Builds on (most cited first, 11 of 11)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems](https://mlsanity.com/paper/2005.01643/) (2020)
- [Diffusion Policies as an Expressive Policy Class for Offline Reinforcement Learning](https://mlsanity.com/paper/2208.06193/) (2022)
- [Keep Doing What Worked: Behavioral Modelling Priors for Offline Reinforcement Learning](https://mlsanity.com/paper/2002.08396/) (2020)
- [Is Value Learning Really the Main Bottleneck in Offline RL?](https://mlsanity.com/paper/2406.09329/) (2024)
- [Offline RL Policies Should be Trained to be Adaptive](https://mlsanity.com/paper/2207.02200/) (2022)
- [Masked Autoencoding for Scalable and Generalizable Decision Making](https://mlsanity.com/paper/2211.12740/) (2022)
- [Reinforcement learning for bandwidth estimation and congestion control in real-time communications](https://mlsanity.com/paper/1912.02222/) (2019)
- [Offline Reinforcement Learning from Datasets with Structured Non-Stationarity](https://mlsanity.com/paper/2405.14114/) (2024)
- [Offline to Online Learning for Real-Time Bandwidth Estimation](https://mlsanity.com/paper/2309.13481/) (2023)
- [Offline Meta-learning for Real-time Bandwidth Estimation](https://mlsanity.com/paper/2409.19867/) (2024)

## Abstract (arXiv)

The difficulty of exploring and training online on real production systems limits the scope of real-time online data/feedback-driven decision making. The most feasible approach is to adopt offline reinforcement learning from limited trajectory samples. However, after deployment, such policies fail due to exogenous factors that temporarily or permanently disturb/alter the transition distribution of the assumed decision process structure induced by offline samples. This results in critical policy failures and generalization errors in sensitive domains like Real-Time Communication (RTC). We solve this crucial problem of identifying robust actions in presence of domain shifts due to unseen exogenous stochastic factors in the wild. As it is impossible to learn generalized offline policies within the support of offline data that are robust to these unseen exogenous disturbances, we propose a novel post-deployment shaping of policies (Streetwise), conditioned on real-time characterization of out-of-distribution sub-spaces. This leads to robust actions in bandwidth estimation (BWE) of network bottlenecks in RTC and in standard benchmarks. Our extensive experimental results on BWE and other standard offline RL benchmark environments demonstrate a significant improvement (≈ 18% on some scenarios) in final returns wrt. end-user metrics over state-of-the-art baselines.