Informativeness Of Reward Functions In Reinforcement Learning

Abstract

Reward functions are central in specifying the task we want a reinforcement learning agent to perform. Given a task and desired optimal behavior, we study the problem of designing informative reward functions so that the designed rewards speed up the agent's convergence. In particular, we consider expert-driven reward design settings where an expert or teacher seeks to provide informative and interpretable rewards to a learning agent. Existing works have considered several different reward design formulations; however, the key challenge is formulating a reward informativeness criterion that adapts w.r.t. the agent's current policy and can be optimized under specified structural constraints to obtain interpretable rewards. In this paper, we propose a novel reward informativeness criterion, a quantitative measure that captures how the agent's current policy will improve if it receives rewards from a specific reward function. We theoretically showcase the utility of the proposed informati

Stats

• citations1
• S2 citations—
• github stars0
• HF likes0
• heat score2.26
• arxiv keydevidze2024informativeness

Related papers

• Reward Design For Reinforcement Learning Agents (2025)0.00
• Designing Rewards For Fast Learning (2022)0.00
• Invariance In Policy Optimisation And Partial Identifiability In Reward Learning (2022)0.00
• Tiered Reward: Designing Rewards For Specification And Fast Learning Of Desired Behavior (2022)0.00
• Pitfalls Of Learning A Reward Function Online (2020)4.52
• On Learning Intrinsic Rewards For Policy Gradient Methods (2018)0.00
• Provably Feedback-efficient Reinforcement Learning Via Active Reward Learning (2023)0.00
• Goodhart's Law In Reinforcement Learning (2023)0.00