paper-with-me

Papers

Curious Explorer: a provable exploration strategy in Policy Learning

2021-06-29 · Marco Miani, Maurizio Parton, Marco Romito

Having access to an exploring restart distribution (the so-called wide coverage assumption) is critical with policy gradient methods. This is due to the fact that, while the objective function is insensitive to updates in unlikely states, the agent may still need improvements in those states in order to reach a nearly optimal payoff. For this reason, wide coverage is used in some form when analyzing theoretical properties of practical policy gradient methods. However, this assumption can be unfeasible in certain environments, for instance when learning is online, or when restarts are possible only from a fixed initial state. In these cases, classical policy gradient algorithms can have very poor convergence properties and sample efficiency. In this paper, we develop Curious Explorer, a novel and simple iterative state space exploration strategy that can be used with any starting distribution $\rho$. Curious Explorer starts from $\rho$, then using intrinsic rewards assigned to the set of poorly visited states produces a sequence of policies, each one more exploratory than the previous one in an informed way, and finally outputs a restart model $\mu$ based on the state visitation distribution of the exploratory policies. Curious Explorer is provable, in the sense that we provide theoretical upper bounds on how often an optimal policy visits poorly visited states. These bounds can be used to prove PAC convergence and sample efficiency results when a PAC optimizer is plugged in Curious Explorer. This allows to achieve global convergence and sample efficiency results without any coverage assumption for REINFORCE, and potentially for any other policy gradient method ensuring PAC convergence with wide coverage. Finally, we plug (the output of) Curious Explorer into REINFORCE and TRPO, and show empirically that it can improve performance in MDPs with challenging exploration.

📄 PDF Abstract BibTeX arXiv:2106.15503

Code (0)

등록된 구현이 없습니다.

Tasks

Policy Gradient Methods

Methods 이 논문이 사용한 방법론

TRPO Trust Region Policy Optimization, or TRPO, is a policy gradient method in reinforcement learning that avoids parameter updates that change the policy too much with a KL…
REINFORCE REINFORCE is a Monte Carlo variant of a policy gradient algorithm in reinforcement learning. The agent collects samples of an episode using its current policy, and uses it to…

Similar Papers 제목 키워드 기반

OVD-Explorer: A General Information-theoretic Exploration Approach for Reinforcement Learning

2021-09-29 · Jinyi Liu, Zhi Wang, Yan Zheng, Jianye Hao 외

Many exploration strategies are built upon the optimism in the face of the uncertainty (OFU) principle for reinforcement learning. However, without considering the aleatoric uncertainty, existing methods may over-explore…

MuJoCoreinforcement-learningReinforcement Learning (RL)

OVD-Explorer: Optimism Should Not Be the Sole Pursuit of Exploration in Noisy Environments

2023-12-19 · Jinyi Liu, Zhi Wang, Yan Zheng, Jianye Hao 외

In reinforcement learning, the optimism in the face of uncertainty (OFU) is a mainstream principle for directing exploration towards less explored areas, characterized by higher uncertainty. However, in the presence of e…

continuous-controlContinuous ControlMuJoCo

LLM-Explorer: A Plug-in Reinforcement Learning Policy Exploration Enhancement Driven by Large Language Models

2025-05-21 · Qianyue Hao, Yiwen Song, Qingmin Liao, Jian Yuan 외

Policy exploration is critical in reinforcement learning (RL), where existing approaches include greedy, Gaussian process, etc. However, these approaches utilize preset stochastic processes and are indiscriminately appli…

MuJoCoReinforcement Learning (RL)

Smaller Models are Natural Explorers for Policy-Level Diversity in GRPO

2026-05-29 · Yiming Ren, Yiran Xu, Zicheng Lin, Chufan Shi 외 arxiv

We identify a new dimension for enhancing rollout diversity in Group Relative Policy Optimization (GRPO) for LLMs. While GRPO relies on diverse rollouts, prevailing strategies primarily increase diversity by injecting mo…

Mathematical Reasoning

Devil is in Narrow Policy: Unleashing Exploration in Driving VLA Models

2026-03-06 · Canyu Chen, Yuguang Yang, Zhewen Tan, Yizhi Wang 외 arxiv

We identify a fundamental Narrow Policy limitation undermining the performance of autonomous VLA models, where driving Imitation Learning (IL) tends to collapse exploration and limit the potential of subsequent Reinforce…

Reinforcement Learning