paper-with-me

홈 › Papers

Learning to Explore in Diverse Reward Settings via Temporal-Difference-Error Maximization

2025-06-16 · Sebastian Griesbach, Carlo D'Eramo

Numerous heuristics and advanced approaches have been proposed for exploration in different settings for deep reinforcement learning. Noise-based exploration generally fares well with dense-shaped rewards and bonus-based exploration with sparse rewards. However, these methods usually require additional tuning to deal with undesirable reward settings by adjusting hyperparameters and noise distributions. Rewards that actively discourage exploration, i.e., with an action cost and no other dense signal to follow, can pose a major challenge. We propose a novel exploration method, Stable Error-seeking Exploration (SEE), that is robust across dense, sparse, and exploration-adverse reward settings. To this endeavor, we revisit the idea of maximizing the TD-error as a separate objective. Our method introduces three design choices to mitigate instability caused by far-off-policy learning, the conflict of interest of maximizing the cumulative TD-error in an episodic setting, and the non-stationary nature of TD-errors. SEE can be combined with off-policy algorithms without modifying the optimization pipeline of the original objective. In our experimental analysis, we show that a Soft-Actor Critic agent with the addition of SEE performs robustly across three diverse reward settings in a variety of tasks without hyperparameter adjustments.

📄 PDF Abstract BibTeX arXiv:2506.13345

Code (1)

sebastian-griesbach/see 공식 구현 pytorch

Tasks

Deep Reinforcement Learning

Similar Papers 제목 키워드 기반

Temporal Difference Uncertainties as a Signal for Exploration

2020-10-05 · Sebastian Flennerhag, Jane X. Wang, Pablo Sprechmann, Francesco Visin 외

An effective approach to exploration in reinforcement learning is to rely on an agent's uncertainty over the optimal policy, which can yield near-optimal exploration strategies in tabular settings. However, in non-tabula…

Almost Sure Convergence of Differential Temporal Difference Learning for Average Reward Markov Decision Processes

2026-02-18 · Ethan Blaser, Jiuqi Wang, Shangtong Zhang arxiv

The average reward is a fundamental performance metric in reinforcement learning (RL) focusing on the long-run performance of an agent. Differential temporal difference (TD) learning algorithms are a major advance for av…

Reinforcement Learning

TDRM: Smooth Reward Models with Temporal Difference for LLM RL and Inference

2025-09-18 · Dan Zhang, Min Cai, Jonathan Light, Ziniu Hu 외 arxiv

Reward models are central to both reinforcement learning (RL) with language models and inference-time verification. However, existing reward models often lack temporal consistency, leading to ineffective policy updates a…

Reinforcement Learning

A Local Temporal Difference Code for Distributional Reinforcement Learning

2020-12-01 · NeurIPS 2020 12 · Pablo Tano, Peter Dayan, Alexandre Pouget

Recent theoretical and experimental results suggest that the dopamine system implements distributional temporal difference backups, allowing learning of the entire distributions of the long-run values of states rather th…

Distributional Reinforcement LearningImputationreinforcement-learningReinforcement Learning+1

Concentration of Cumulative Reward in Markov Decision Processes

2024-11-27 · Borna Sayedana, Peter E. Caines, Aditya Mahajan

In this paper, we investigate the concentration properties of cumulative rewards in Markov Decision Processes (MDPs), focusing on both asymptotic and non-asymptotic settings. We introduce a unified approach to characteri…