paper-with-me

Papers

RUDDER: Return Decomposition for Delayed Rewards

2018-06-20 · NeurIPS 2019 12 · Jose A. Arjona-Medina, Michael Gillhofer, Michael Widrich, Thomas Unterthiner, Johannes Brandstetter, Sepp Hochreiter

We propose RUDDER, a novel reinforcement learning approach for delayed rewards in finite Markov decision processes (MDPs). In MDPs the Q-values are equal to the expected immediate reward plus the expected future rewards. The latter are related to bias problems in temporal difference (TD) learning and to high variance problems in Monte Carlo (MC) learning. Both problems are even more severe when rewards are delayed. RUDDER aims at making the expected future rewards zero, which simplifies Q-value estimation to computing the mean of the immediate reward. We propose the following two new concepts to push the expected future rewards toward zero. (i) Reward redistribution that leads to return-equivalent decision processes with the same optimal policies and, when optimal, zero expected future rewards. (ii) Return decomposition via contribution analysis which transforms the reinforcement learning task into a regression task at which deep learning excels. On artificial tasks with delayed rewards, RUDDER is significantly faster than MC and exponentially faster than Monte Carlo Tree Search (MCTS), TD({\lambda}), and reward shaping approaches. At Atari games, RUDDER on top of a Proximal Policy Optimization (PPO) baseline improves the scores, which is most prominent at games with delayed rewards. Source code is available at \url{https://github.com/ml-jku/rudder} and demonstration videos at \url{https://goo.gl/EQerZV}.

📄 PDF Abstract BibTeX arXiv:1806.07857

Code (2)

ml-jku/baselines-rudder 공식 구현 tf
ml-jku/rudder 공식 구현 pytorch

Tasks

Atari Gamesreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Similar Papers 제목 키워드 기반

Align-RUDDER: Learning From Few Demonstrations by Reward Redistribution

2020-09-29 · Vihang P. Patil, Markus Hofmarcher, Marius-Constantin Dinu, Matthias Dorfer 외

Reinforcement learning algorithms require many samples when solving complex hierarchical tasks with sparse and delayed rewards. For such complex tasks, the recently proposed RUDDER uses reward redistribution to leverage …

General Reinforcement LearningMinecraftMultiple Sequence AlignmentSafe Exploration

Episodic Return Decomposition by Difference of Implicitly Assigned Sub-Trajectory Reward

2023-12-17 · Haoxin Lin, Hongqiu Wu, Jiaji Zhang, Yihao Sun 외

Real-world decision-making problems are usually accompanied by delayed rewards, which affects the sample efficiency of Reinforcement Learning, especially in the extremely delayed case where the only feedback is the episo…

Decision Making

Interpretable Reward Redistribution in Reinforcement Learning: A Causal Approach

2023-05-28 · NeurIPS 2023 11 · Yudi Zhang, Yali Du, Biwei Huang, Ziyan Wang 외

A major challenge in reinforcement learning is to determine which state-action pairs are responsible for future rewards that are delayed. Reward redistribution serves as a solution to re-assign credits for each time step…

reinforcement-learningReinforcement Learning

Learning Long-Term Reward Redistribution via Randomized Return Decomposition

2021-11-26 · ICLR 2022 4 · Zhizhou Ren, Ruihan Guo, Yuan Zhou, Jian Peng

Many practical applications of reinforcement learning require agents to learn from sparse and delayed rewards. It challenges the ability of agents to attribute their actions to future outcomes. In this paper, we consider…

Attributereinforcement-learningReinforcement LearningReinforcement Learning (RL)

Towards Return Parity in Markov Decision Processes

2021-11-19 · Jianfeng Chi, Jian Shen, Xinyi Dai, Weinan Zhang 외

Algorithmic decisions made by machine learning models in high-stakes domains may have lasting impacts over time. However, naive applications of standard fairness criterion in static settings over temporal domains may lea…

FairnessRecommendation Systems