paper-with-me

Papers

A Generalized Algorithm for Multi-Objective Reinforcement Learning and Policy Adaptation

2019-08-21 · NeurIPS 2019 12 · Runzhe Yang, Xingyuan Sun, Karthik Narasimhan

We introduce a new algorithm for multi-objective reinforcement learning (MORL) with linear preferences, with the goal of enabling few-shot adaptation to new tasks. In MORL, the aim is to learn policies over multiple competing objectives whose relative importance (preferences) is unknown to the agent. While this alleviates dependence on scalar reward design, the expected return of a policy can change significantly with varying preferences, making it challenging to learn a single model to produce optimal policies under different preference conditions. We propose a generalized version of the Bellman equation to learn a single parametric representation for optimal policies over the space of all possible preferences. After an initial learning phase, our agent can execute the optimal policy under any given preference, or automatically infer an underlying preference with very few samples. Experiments across four different domains demonstrate the effectiveness of our approach.

📄 PDF Abstract BibTeX arXiv:1908.08342

Code (4)

RunzheYang/MORL 공식 구현 pytorch
lucasalegre/mo-gym
lucasalegre/morl-baselines pytorch
sunnyyzj/morl-baselines pytorch

Tasks

Multi-Objective Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Similar Papers 제목 키워드 기반

Generalized Off-Policy Actor-Critic

2019-03-27 · NeurIPS 2019 12 · Shangtong Zhang, Wendelin Boehmer, Shimon Whiteson

We propose a new objective, the counterfactual objective, unifying existing objectives for off-policy policy gradient algorithms in the continuing reinforcement learning (RL) setting. Compared to the commonly used excurs…

counterfactualMuJoCoreinforcement-learningReinforcement Learning+1

A Generalized Projected Bellman Error for Off-policy Value Estimation in Reinforcement Learning

2021-04-28 · Andrew Patterson, Adam White, Martha White

Many reinforcement learning algorithms rely on value estimation, however, the most widely used algorithms -- namely temporal difference algorithms -- can diverge under both off-policy sampling and nonlinear function appr…

reinforcement-learningReinforcement Learning (RL)

gTLO: A Generalized and Non-linear Multi-Objective Deep Reinforcement Learning Approach

2022-04-11 · Johannes Dornheim

In real-world decision optimization, often multiple competing objectives must be taken into account. Following classical reinforcement learning, these objectives have to be combined into a single reward function. In cont…

Deep Reinforcement LearningDeep-Sea Treasure, Image versionMulti-Objective Reinforcement Learningreinforcement-learning+2

Neural PPO-Clip Attains Global Optimality: A Hinge Loss Perspective

2021-10-26 · Nai-Chieh Huang, Ping-Chun Hsieh, Kuo-Hao Ho, Hsuan-Yu Yao 외

Policy optimization is a fundamental principle for designing reinforcement learning algorithms, and one example is the proximal policy optimization algorithm with a clipped surrogate objective (PPO-Clip), which has been …

Deep Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Enhancing Online Reinforcement Learning with Meta-Learned Objective from Offline Data

2025-01-13 · Shilong Deng, Zetao Zheng, Hongcai He, Paul Weng 외

A major challenge in Reinforcement Learning (RL) is the difficulty of learning an optimal policy from sparse rewards. Prior works enhance online RL with conventional Imitation Learning (IL) via a handcrafted auxiliary ob…

Imitation LearningMuJoCoReinforcement Learning (RL)