# Context-Sensitive Abstractions for Reinforcement Learning with Parameterized Actions

arXiv: https://arxiv.org/abs/2512.20831 · HTML: https://mlsanity.com/paper/2512.20831/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Deep RL algorithms and representations, one of 15 directions in Deep reinforcement learning methods.
- Builds on 20 of its 29 references that are in the map.
- First posted on arXiv 23 Dec 2025.

## Placed in

- Deep reinforcement learning methods / [Deep RL algorithms and representations](https://mlsanity.com/deeprl/deep-rl-algorithms-and-representations/)

## Builds on (most cited first, 20 of 20)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor](https://mlsanity.com/paper/1801.01290/) (2018)
- [Continuous control with deep reinforcement learning](https://mlsanity.com/paper/1509.02971/) (2015)
- [Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model](https://mlsanity.com/paper/1911.08265/) (2019)
- [TD-MPC2: Scalable, Robust World Models for Continuous Control](https://mlsanity.com/paper/2310.16828/) (2023)
- [Data-Efficient Hierarchical Reinforcement Learning](https://mlsanity.com/paper/1805.08296/) (2018)
- [Reward Machines: Exploiting Reward Function Structure in Reinforcement Learning](https://mlsanity.com/paper/2010.03950/) (2020)
- [Deep Reinforcement Learning in Parameterized Action Space](https://mlsanity.com/paper/1511.04143/) (2015)
- [Reinforcement Learning with Parameterized Actions](https://mlsanity.com/paper/1509.01644/) (2015)
- [Parametrized Deep Q-Networks Learning: Reinforcement Learning with Discrete-Continuous Hybrid Action Space](https://mlsanity.com/paper/1810.06394/) (2018)
- [Hybrid Actor-Critic Reinforcement Learning in Parameterized Action Space](https://mlsanity.com/paper/1903.01344/) (2019)
- [HyAR: Addressing Discrete-Continuous Action Reinforcement Learning via Hybrid Action Representation](https://mlsanity.com/paper/2109.05490/) (2021)
- [Bridging RL Theory and Practice with the Effective Horizon](https://mlsanity.com/paper/2304.09853/) (2023)
- [Multi-Pass Q-Networks for Deep Reinforcement Learning with Parameterised Action Spaces](https://mlsanity.com/paper/1905.04388/) (2019)
- [Continuous Control with Coarse-to-fine Reinforcement Learning](https://mlsanity.com/paper/2407.07787/) (2024)
- [Building Minimal and Reusable Causal State Abstractions for Reinforcement Learning](https://mlsanity.com/paper/2401.12497/) (2024)
- [Polynomial Time Reinforcement Learning in Factored State MDPs with Linear Value Functions](https://mlsanity.com/paper/2107.05187/) (2021)
- [Learning Abstract World Model for Value-preserving Planning with Options](https://mlsanity.com/paper/2406.15850/) (2024)
- [Autonomous Option Invention for Continual Hierarchical Reinforcement Learning and Planning](https://mlsanity.com/paper/2412.16395/) (2024)
- [Expediting Reinforcement Learning by Incorporating Knowledge About Temporal Causality in the Environment](https://mlsanity.com/paper/2510.15456/) (2025)

## Abstract (arXiv)

Real-world sequential decision-making often involves parameterized action spaces that require both, decisions regarding discrete actions and decisions about continuous action parameters governing how an action is executed. Existing approaches exhibit severe limitations in this setting -- planning methods demand hand-crafted action models, and standard reinforcement learning (RL) algorithms are designed for either discrete or continuous actions but not both, and the few RL methods that handle parameterized actions typically rely on domain-specific engineering and fail to exploit the latent structure of these spaces. This paper extends the scope of RL algorithms to long-horizon, sparse-reward settings with parameterized actions by enabling agents to autonomously learn both state and action abstractions online. We introduce algorithms that progressively refine these abstractions during learning, increasing fine-grained detail in the critical regions of the state-action space where greater resolution improves performance. Across several continuous-state, parameterized-action domains, our abstraction-driven approach enables TD(λ) to achieve markedly higher sample efficiency than state-of-the-art baselines.