paper-with-me

Papers

Continual Reinforcement Learning with Diversity Exploration and Adversarial Self-Correction

2019-06-21 · Fengda Zhu, Xiaojun Chang, Runhao Zeng, Mingkui Tan

Deep reinforcement learning has made significant progress in the field of continuous control, such as physical control and autonomous driving. However, it is challenging for a reinforcement model to learn a policy for each task sequentially due to catastrophic forgetting. Specifically, the model would forget knowledge it learned in the past when trained on a new task. We consider this challenge from two perspectives: i) acquiring task-specific skills is difficult since task information and rewards are not highly related; ii) learning knowledge from previous experience is difficult in continuous control domains. In this paper, we introduce an end-to-end framework namely Continual Diversity Adversarial Network (CDAN). We first develop an unsupervised diversity exploration method to learn task-specific skills using an unsupervised objective. Then, we propose an adversarial self-correction mechanism to learn knowledge by exploiting past experience. The two learning procedures are presumably reciprocal. To evaluate the proposed method, we propose a new continuous reinforcement learning environment named Continual Ant Maze (CAM) and a new metric termed Normalized Shorten Distance (NSD). The experimental results confirm the effectiveness of diversity exploration and self-correction. It is worthwhile noting that our final result outperforms baseline by 18.35% in terms of NSD, and 0.61 according to the average reward.

📄 PDF Abstract BibTeX arXiv:1906.09205

Code (0)

등록된 구현이 없습니다.

Tasks

Autonomous Drivingcontinuous-controlContinuous ControlDeep Reinforcement LearningDiversityreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Similar Papers 제목 키워드 기반

Demonstration-Guided Continual Reinforcement Learning in Dynamic Environments

2025-12-21 · Xue Yang, Michael Schukat, Junlin Lu, Patrick Mannion 외 arxiv

Reinforcement learning (RL) excels in various applications but struggles in dynamic environments where the underlying Markov decision process evolves. Continual reinforcement learning (CRL) enables RL agents to continual…

Reinforcement Learning

Task diversity produces systematic transfer but inhibits continual reinforcement learning

2026-05-30 · Purab Seth, Neil Shah, Kunal Jha, Samuel J. Gershman 외 arxiv

Continual reinforcement learning aims to produce agents that learn not only to improve at their current tasks but also to adapt as task distributions change. Training an agent on many diverse tasks can induce zero-shot g…

Zero-shot GeneralizationReinforcement LearningContinual Learning

HAMMER: Hamiltonian Curiosity Augmented Large Language Model Reinforcement

2025-09-25 · Ming Yang, Xiaofan Li, Zhiyuan Ma, Dengliang Shi 외 arxiv

Recent curriculum reinforcement learning for large language models (LLMs) typically rely on difficulty-based annotations for data filtering and ordering. However, such methods suffer from local optimization, where contin…

Reinforcement Learning

Relay Hindsight Experience Replay: Self-Guided Continual Reinforcement Learning for Sequential Object Manipulation Tasks with Sparse Rewards

2022-08-01 · Yongle Luo, Yuxin Wang, Kun Dong, Qiang Zhang 외

Exploration with sparse rewards remains a challenging research problem in reinforcement learning (RL). Especially for sequential object manipulation tasks, the RL agent always receives negative rewards until completing a…

FetchPush-v1Reinforcement Learning (RL)Robot Manipulation

SOE: Sample-Efficient Robot Policy Self-Improvement via On-Manifold Exploration

2025-09-23 · Yang Jin, Jun Lv, Han Xue, Wendi Chen 외 arxiv

Intelligent agents progress by continually refining their capabilities through actively exploring environments. Yet robot policies often lack sufficient exploration capability due to action mode collapse. Existing method…