Hybrid Policies Using Inverse Rewards for Reinforcement Learning

2018-09-27 · Yao Shi, Tian Xia, Guanjun Zhao, Xin Gao

This paper puts forward a broad-spectrum improvement for reinforcement learning algorithms, which combines the policies using original rewards and inverse (negative) rewards. The policies using inverse rewards are competitive with the original policies, and help the original policies correct their mis-actions. We have proved the convergence of the inverse policies. The experiments for some games in OpenAI gym show that the hybrid polices based on deep Q-learning, double Q-learning, and on-policy actor-critic obtain the rewards up to 63.8%, 97.8%, and 54.7% more than the original algorithms. The improved polices are more stable than the original policies as well.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

OpenAI GymQ-Learningreinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Adversarial Imitation via Variational Inverse Reinforcement Learning

2018-09-17 · ICLR 2019 5 · Ahmed H. Qureshi, Byron Boots, Michael C. Yip

We consider a problem of learning the reward and policy from expert examples under unknown dynamics. Our proposed method builds on the framework of generative adversarial networks and introduces the empowerment-regulariz…

reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)Transfer Learning

oIRL: Robust Adversarial Inverse Reinforcement Learning with Temporally Extended Actions

2020-02-20 · David Venuto, Jhelum Chakravorty, Leonard Boussioux, Junhao Wang 외

Explicit engineering of reward functions for given environments has been a major hindrance to reinforcement learning methods. While Inverse Reinforcement Learning (IRL) is a solution to recover reward functions from demo…

continuous-control Continuous Control reinforcement-learning Reinforcement Learning+2

BC-IRL: Learning Generalizable Reward Functions from Demonstrations

2023-03-28 · Andrew Szot, Amy Zhang, Dhruv Batra, Zsolt Kira 외

How well do reward functions learned with inverse reinforcement learning (IRL) generalize? We illustrate that state-of-the-art IRL algorithms, which maximize a maximum-entropy objective, learn rewards that overfit to the…

reinforcement-learning Reinforcement Learning

GRACE: A Language Model Framework for Explainable Inverse Reinforcement Learning

2025-10-02 · Silvia Sapora, Devon Hjelm, Alexander Toshev, Omar Attia 외 arxiv

Inverse Reinforcement Learning aims to recover reward models from expert demonstrations, but traditional methods yield black-box models that are difficult to interpret and debug. In this work, we introduce GRACE (Generat…

Reinforcement Learning

Versatile Inverse Reinforcement Learning via Cumulative Rewards

2021-11-15 · Niklas Freymuth, Philipp Becker, Gerhard Neumann

Inverse Reinforcement Learning infers a reward function from expert demonstrations, aiming to encode the behavior and intentions of the expert. Current approaches usually do this with generative and uni-modal models, mea…

reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)