paper-with-me

Papers

On the Expressivity of Neural Networks for Deep Reinforcement Learning

2019-10-14 · ICML 2020 1 · Kefan Dong, Yuping Luo, Tengyu Ma

We compare the model-free reinforcement learning with the model-based approaches through the lens of the expressive power of neural networks for policies, $Q$-functions, and dynamics. We show, theoretically and empirically, that even for one-dimensional continuous state space, there are many MDPs whose optimal $Q$-functions and policies are much more complex than the dynamics. We hypothesize many real-world MDPs also have a similar property. For these MDPs, model-based planning is a favorable algorithm, because the resulting policies can approximate the optimal policy significantly better than a neural network parameterization can, and model-free or model-based policy optimization rely on policy parameterization. Motivated by the theory, we apply a simple multi-step model-based bootstrapping planner (BOOTS) to bootstrap a weak $Q$-function into a stronger policy. Empirical results show that applying BOOTS on top of model-based or model-free policy optimization algorithms at the test time improves the performance on MuJoCo benchmark tasks.

📄 PDF Abstract BibTeX arXiv:1910.05927

Code (1)

roosephu/boots 공식 구현 tf

Tasks

Deep Reinforcement LearningMuJoCoreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Methods 이 논문이 사용한 방법론

Test 설명 없음

Similar Papers 제목 키워드 기반

Balancing Expressivity and Robustness: Constrained Rational Activations for Reinforcement Learning

2025-07-19 · Rafał Surdej, Michał Bortkiewicz, Alex Lewandowski, Mateusz Ostaszewski 외 arxiv

Trainable activation functions, whose parameters are optimized alongside network weights, offer increased expressivity compared to fixed activation functions. Specifically, trainable activation functions defined as ratio…

Reinforcement LearningContinuous ControlContinual Learning

MAG-GNN: Reinforcement Learning Boosted Graph Neural Network

2023-10-29 · NeurIPS 2023 11

While Graph Neural Networks (GNNs) recently became powerful tools in graph learning tasks, considerable efforts have been spent on improving GNNs' structural encoding ability. A particular line of work proposed subgraph …

Combinatorial OptimizationGraph LearningGraph Neural Networkreinforcement-learning+2

On The Expressivity of Objective-Specification Formalisms in Reinforcement Learning

2023-10-18 · Rohan Subramani, Marcus Williams, Max Heitmann, Halfdan Holm 외

Most algorithms in reinforcement learning (RL) require that the objective is formalised with a Markovian reward function. However, it is well-known that certain tasks cannot be expressed by means of an objective in the M…

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

DisCo RL: Distribution-Conditioned Reinforcement Learning for General-Purpose Policies

2021-04-23 · Soroush Nasiriany, Vitchyr H. Pong, Ashvin Nair, Alexander Khazatsky 외

Can we use reinforcement learning to learn general-purpose policies that can perform a wide range of different tasks, resulting in flexible and reusable skills? Contextual policies provide this capability in principle, b…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)Robot Manipulation

Expressivity and Statistical Trade-offs in Diffusion Policy Learning

2026-07-08 · Viet Vu, Renyuan Xu, Jiacheng Zhang, Yufei Zhang arxiv

Diffusion-based policies have recently emerged as powerful policy parameterizations for reinforcement learning, representing state-conditioned action distributions as terminal laws of diffusion processes with parameteriz…

Reinforcement Learning