paper-with-me

홈 › Papers

Self-Supervised Online Reward Shaping in Sparse-Reward Environments

2021-03-08 · Farzan Memarian, Wonjoon Goo, Rudolf Lioutikov, Scott Niekum, Ufuk Topcu

We introduce Self-supervised Online Reward Shaping (SORS), which aims to improve the sample efficiency of any RL algorithm in sparse-reward environments by automatically densifying rewards. The proposed framework alternates between classification-based reward inference and policy update steps -- the original sparse reward provides a self-supervisory signal for reward inference by ranking trajectories that the agent observes, while the policy update is performed with the newly inferred, typically dense reward function. We introduce theory that shows that, under certain conditions, this alteration of the reward function will not change the optimal policy of the original MDP, while potentially increasing learning speed significantly. Experimental results on several sparse-reward environments demonstrate that, across multiple domains, the proposed algorithm is not only significantly more sample efficient than a standard RL baseline using sparse rewards, but, at times, also achieves similar sample efficiency compared to when hand-designed dense reward functions are used.

📄 PDF Abstract BibTeX arXiv:2103.04529

Code (1)

hiwonjoon/IROS2021_SORS 공식 구현 tf

Similar Papers 제목 키워드 기반

ARMS: Automatic Reward Shaping for Sparse-Reward Multi-Agent Reinforcement Learning

2026-05-22 · Elie Abboud, Oren Gal arxiv

Sparse rewards are a major bottleneck in multi-agent reinforcement learning (MARL), where simultaneous learning induces non-stationarity and makes reward design especially delicate. Reward shaping can accelerate learning…

Multi-agent Reinforcement Learning

Shaping Sparse Rewards in Reinforcement Learning: A Semi-supervised Approach

2025-01-31 · Wenyun Li, Wenjie Huang

In many real-world scenarios, reward signal for agents are exceedingly sparse, making it challenging to learn an effective reward function for reward shaping. To address this issue, our approach performs reward shaping n…

Data Augmentationreinforcement-learningReinforcement Learning

Reward prediction for representation learning and reward shaping

2021-05-07 · Hlynur Davíð Hlynsson, Laurenz Wiskott

One of the fundamental challenges in reinforcement learning (RL) is the one of data efficiency: modern algorithms require a very large number of training samples, especially compared to humans, for solving environments w…

PredictionReinforcement Learning (RL)Representation Learning

ORSO: Accelerating Reward Design via Online Reward Selection and Policy Optimization

2024-10-17 · Chen Bo Calvin Zhang, Zhang-Wei Hong, Aldo Pacchiano, Pulkit Agrawal

Reward shaping is critical in reinforcement learning (RL), particularly for complex tasks where sparse rewards can hinder learning. However, choosing effective shaping rewards from a set of reward functions in a computat…

continuous-controlContinuous ControlModel SelectionReinforcement Learning (RL)

Highly Efficient Self-Adaptive Reward Shaping for Reinforcement Learning

2024-08-06 · Haozhe Ma, Zhengding Luo, Thanh Vinh Vo, Kuankuan Sima 외

Reward shaping is a technique in reinforcement learning that addresses the sparse-reward problem by providing more frequent and informative rewards. We introduce a self-adaptive and highly efficient reward shaping mechan…

Continuous ControlDensity Estimationreinforcement-learningReinforcement Learning