Learning to Utilize Shaping Rewards: A New Approach of Reward Shaping

Abstract

Reward shaping is an effective technique for incorporating domain knowledge into reinforcement learning (RL). Existing approaches such as potential-based reward shaping normally make full use of a given shaping reward function. However, since the transformation of human knowledge into numeric reward values is often imperfect due to reasons such as human cognitive bias, completely utilizing the shaping reward function may fail to improve the performance of RL algorithms. In this paper, we consider the problem of adaptively utilizing a given shaping reward function. We formulate the utilization of shaping rewards as a bi-level optimization problem, where the lower level is to optimize policy using the shaping rewards and the upper level is to optimize a parameterized shaping weight function for true reward maximization. We formally derive the gradient of the expected true reward with respect to the shaping weight function parameters and accordingly propose three learning algorithms based on different assumptions. Experiments in sparse-reward cartpole and MuJoCo environments show that our algorithms can fully exploit beneficial shaping rewards, and meanwhile ignore unbeneficial shaping rewards or even transform them into beneficial ones.

Accepted by NeurIPS2020

References in corpus (1)

• Reward Shaping via Meta-Learning

Cited by in corpus (8)

• Automated Reinforcement Learning (AutoRL): A Survey and Open Problems
• From Screens to Scenes: A Survey of Embodied AI in Healthcare
• Bridging adaptive management and reinforcement learning for more robust decisions
• ReLAX: Reinforcement Learning Agent eXplainer for Arbitrary Predictive Models
• Model-Based Safe Reinforcement Learning with Time-Varying State and Control Constraints: An Application to Intelligent Vehicles
• Heuristic-Guided Reinforcement Learning
• Embedding Contextual Information through Reward Shaping in Multi-Agent Learning: A Case Study from Google Football
• Learning in Sparse Rewards settings through Quality-Diversity algorithms