# Composable Action-Conditioned Predictors: Flexible Off-Policy Learning for Robot Navigation

arXiv: https://arxiv.org/abs/1810.07167 · HTML: https://mlsanity.com/paper/1810.07167/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Oct 2018.

## Built on by (most cited first, 9 of 9)

- [Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems](https://mlsanity.com/paper/2005.01643/) (2020)
- [COMBO: Conservative Offline Model-Based Policy Optimization](https://mlsanity.com/paper/2102.08363/) (2021)
- [Believe What You See: Implicit Constraint Approach for Offline Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2106.03400/) (2021)
- [Offline Reinforcement Learning with Reverse Model-based Imagination](https://mlsanity.com/paper/2110.00188/) (2021)
- [Laminar: A Scalable Asynchronous RL Post-Training Framework](https://mlsanity.com/paper/2510.12633/) (2025)
- [Offline Reinforcement Learning for Visual Navigation](https://mlsanity.com/paper/2212.08244/) (2022)
- [Primal-Dual Spectral Representation for Off-policy Evaluation](https://mlsanity.com/paper/2410.17538/) (2024)
- [Deep Learning for Embodied Vision Navigation: A Survey](https://mlsanity.com/paper/2108.04097/) (2021)
- [Aligning Flow Map Policies with Optimal Q-Guidance](https://mlsanity.com/paper/2605.12416/) (2026)

## Abstract (arXiv)

A general-purpose intelligent robot must be able to learn autonomously and be able to accomplish multiple tasks in order to be deployed in the real world. However, standard reinforcement learning approaches learn separate task-specific policies and assume the reward function for each task is known a priori. We propose a framework that learns event cues from off-policy data, and can flexibly combine these event cues at test time to accomplish different tasks. These event cue labels are not assumed to be known a priori, but are instead labeled using learned models, such as computer vision detectors, and then `backed up' in time using an action-conditioned predictive model. We show that a simulated robotic car and a real-world RC car can gather data and train fully autonomously without any human-provided labels beyond those needed to train the detectors, and then at test-time be able to accomplish a variety of different tasks. Videos of the experiments and code can be found at https://github.com/gkahn13/CAPs