Scaling Internal-State Policy-Gradient Methods for POMDPs

2025-12-02 · Douglas Aberdeen, Jonathan Baxter arxiv

Policy-gradient methods have received increased attention recently as a mechanism for learning to act in partially observable environments. They have shown promise for problems admitting memoryless policies but have been less successful when memory is required. In this paper we develop several improved algorithms for learning policies with memory in an infinite-horizon setting -- directly when a known model of the environment is available, and via simulation otherwise. We compare these algorithms on some large POMDPs, including noisy robot navigation and multi-agent problems.

📄 PDF Abstract BibTeX arXiv:2512.03204

Code (0)

등록된 구현이 없습니다.

Tasks

Robot Navigation

Learning to Play Pong using Policy Gradient Learning

2018-07-23 · Somnuk Phon-Amnuaisuk

Activities in reinforcement learning (RL) revolve around learning the Markov decision process (MDP) model, in particular, the following parameters: state values, V; state-action values, Q; and policy, pi. These parameter…

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

Scaling Policy Gradient Quality-Diversity with Massive Parallelization via Behavioral Variations

2025-01-30 · Konstantinos Mitsides, Maxence Faldor, Antoine Cully

Quality-Diversity optimization comprises a family of evolutionary algorithms aimed at generating a collection of diverse and high-performing solutions. MAP-Elites (ME), a notable example, is used effectively in fields li…

Diversity Evolutionary Algorithms GPU

Policy Gradient Methods for Non-Markovian Reinforcement Learning

2026-05-11 · Avik Kar, Siddharth Chandak, Rahul Singh, Soumitra Sinhahajari 외 arxiv

We study policy gradient methods for reinforcement learning in non-Markovian decision processes (NMDPs), where observations and rewards depend on the entire interaction history. To handle this dependence, the agent maint…

Reinforcement Learning

Verifier-Free RL for LLMs via Intrinsic Gradient-Norm Reward

2026-05-11 · Xuexiang Wen, Hang Yu, Linchao Zhu, Gaoang Wang arxiv

While Reinforcement Learning with Verifiable Rewards (RLVR) has recently emerged as a promising post-training paradigm for Large Language Models (LLMs), its dependency on the gold label or domain-specific verifiers limit…

Reinforcement Learning Mathematical Reasoning

The Option-Critic Architecture

2016-09-16 · Pierre-Luc Bacon, Jean Harb, Doina Precup

Temporal abstraction is key to scaling up learning and planning in reinforcement learning. While planning with temporally extended actions is well understood, creating such abstractions autonomously from data has remaine…

reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)