Detecting Rewards Deterioration In Episodic Reinforcement Learning

Abstract

In many RL applications, once training ends, it is vital to detect any deterioration in the agent performance as soon as possible. Furthermore, it often has to be done without modifying the policy and under minimal assumptions regarding the environment. In this paper, we address this problem by focusing directly on the rewards and testing for degradation. We consider an episodic framework, where the rewards within each episode are not independent, nor identically-distributed, nor Markov. We present this problem as a multivariate mean-shift detection problem with possibly partial observations. We define the mean-shift in a way corresponding to deterioration of a temporal signal (such as the rewards), and derive a test for this problem with optimal statistical power. Empirically, on deteriorated rewards in control problems (generated using various environment modifications), the test is demonstrated to be more powerful than standard tests - often by orders of magnitude. We also suggest a

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keygreenberg2020detecting

Related papers

• Disturbing Reinforcement Learning Agents With Corrupted Rewards (2021)0.00
• Non-stationary Risk-sensitive Reinforcement Learning: Near-optimal Dynamic Regret, Adaptive Detection, And Separation Design (2022)3.58
• The Distributional Reward Critic Framework For Reinforcement Learning Under Perturbed Rewards (2024)0.00
• Reinforcement Learning With Non-ergodic Reward Increments: Robustness Via Ergodicity Transformations (2023)0.00
• Assessing The Impact Of Distribution Shift On Reinforcement Learning Performance (2024)0.00
• Episodic Return Decomposition By Difference Of Implicitly Assigned Sub-trajectory Reward (2023)0.00
• Model-agnostic Solutions For Deep Reinforcement Learning In Non-ergodic Contexts (2026)0.00
• DEIR: Efficient And Robust Exploration Through Discriminative-model-based Episodic Intrinsic Rewards (2023)0.00