# Utilizing Prior Solutions for Reward Shaping and Composition in Entropy-Regularized Reinforcement Learning

arXiv: https://arxiv.org/abs/2212.01174 · HTML: https://mlsanity.com/paper/2212.01174/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 18 references that are in the map.
- First posted on arXiv 2 Dec 2022.

## Builds on (most cited first, 9 of 9)

- [Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor](https://mlsanity.com/paper/1801.01290/) (2018)
- [OpenAI Gym](https://mlsanity.com/paper/1606.01540/) (2016)
- [Reinforcement Learning with Deep Energy-Based Policies](https://mlsanity.com/paper/1702.08165/) (2017)
- [Reinforcement Learning and Control as Probabilistic Inference: Tutorial and Review](https://mlsanity.com/paper/1805.00909/) (2018)
- [Maximum Entropy RL (Provably) Solves Some Robust RL Problems](https://mlsanity.com/paper/2103.06257/) (2021)
- [MCP: Learning Composable Hierarchical Control with Multiplicative Compositional Policies](https://mlsanity.com/paper/1905.09808/) (2019)
- [Composable Deep Reinforcement Learning for Robotic Manipulation](https://mlsanity.com/paper/1803.06773/) (2018)
- [Identifiability in inverse reinforcement learning](https://mlsanity.com/paper/2106.03498/) (2021)
- [A Boolean Task Algebra for Reinforcement Learning](https://mlsanity.com/paper/2001.01394/) (2020)

## Built on by (most cited first, 8 of 8)

- [Highly Efficient Self-Adaptive Reward Shaping for Reinforcement Learning](https://mlsanity.com/paper/2408.03029/) (2024)
- [Average-Reward Soft Actor-Critic](https://mlsanity.com/paper/2501.09080/) (2025)
- [Boosting Soft Q-Learning by Bounding](https://mlsanity.com/paper/2406.18033/) (2024)
- [Bounding the Optimal Value Function in Compositional Reinforcement Learning](https://mlsanity.com/paper/2303.02557/) (2023)
- [Semi-supervised Anomaly Detection via Adaptive Reinforcement Learning-Enabled Method with Causal Inference for Sensor Signals](https://mlsanity.com/paper/2405.06925/) (2024)
- [Constrained Sliced Wasserstein Embedding](https://mlsanity.com/paper/2506.02203/) (2025)
- [Leveraging Prior Knowledge in Reinforcement Learning via Double-Sided Bounds on the Value Function](https://mlsanity.com/paper/2302.09676/) (2023)
- [Reinforcement Learning for Control of Non-Markovian Cellular Population Dynamics](https://mlsanity.com/paper/2410.08439/) (2024)

## Abstract (arXiv)

In reinforcement learning (RL), the ability to utilize prior knowledge from previously solved tasks can allow agents to quickly solve new problems. In some cases, these new problems may be approximately solved by composing the solutions of previously solved primitive tasks (task composition). Otherwise, prior knowledge can be used to adjust the reward function for a new problem, in a way that leaves the optimal policy unchanged but enables quicker learning (reward shaping). In this work, we develop a general framework for reward shaping and task composition in entropy-regularized RL. To do so, we derive an exact relation connecting the optimal soft value functions for two entropy-regularized RL problems with different reward functions and dynamics. We show how the derived relation leads to a general result for reward shaping in entropy-regularized RL. We then generalize this approach to derive an exact relation connecting optimal value functions for the composition of multiple tasks in entropy-regularized RL. We validate these theoretical contributions with experiments showing that reward shaping and task composition lead to faster learning in various settings.