paper-with-me

Papers

Free from Bellman Completeness: Trajectory Stitching via Model-based Return-conditioned Supervised Learning

2023-10-30 · Zhaoyi Zhou, Chuning Zhu, Runlong Zhou, Qiwen Cui, Abhishek Gupta, Simon Shaolei Du

Off-policy dynamic programming (DP) techniques such as $Q$-learning have proven to be important in sequential decision-making problems. In the presence of function approximation, however, these techniques often diverge due to the absence of Bellman completeness in the function classes considered, a crucial condition for the success of DP-based methods. In this paper, we show how off-policy learning techniques based on return-conditioned supervised learning (RCSL) are able to circumvent these challenges of Bellman completeness, converging under significantly more relaxed assumptions inherited from supervised learning. We prove there exists a natural environment in which if one uses two-layer multilayer perceptron as the function approximator, the layer width needs to grow linearly with the state space size to satisfy Bellman completeness while a constant layer width is enough for RCSL. These findings take a step towards explaining the superior empirical performance of RCSL methods compared to DP-based methods in environments with near-optimal datasets. Furthermore, in order to learn from sub-optimal datasets, we propose a simple framework called MBRCSL, granting RCSL methods the ability of dynamic programming to stitch together segments from distinct trajectories. MBRCSL leverages learned dynamics models and forward sampling to accomplish trajectory stitching while avoiding the need for Bellman completeness that plagues all dynamic programming algorithms. We propose both theoretical analysis and experimental evaluation to back these claims, outperforming state-of-the-art model-free and model-based offline RL algorithms across several simulated robotics problems.

📄 PDF Abstract BibTeX arXiv:2310.19308

Code (1)

zhaoyizhou1123/mbrcsl 공식 구현 pytorch

Tasks

Decision MakingOffline RLQ-LearningSequential Decision Making

Similar Papers 제목 키워드 기반

Adaptive $Q$-Aid for Conditional Supervised Learning in Offline Reinforcement Learning

2024-02-03 · Jeonghye Kim, Suyoung Lee, Woojun Kim, Youngchul Sung

Offline reinforcement learning (RL) has progressed with return-conditioned supervised learning (RCSL), but its lack of stitching ability remains a limitation. We introduce $Q$-Aided Conditional Supervised Learning (QCS),…

Offline RLReinforcement Learning (RL)

In-Dataset Trajectory Return Regularization for Offline Preference-based Reinforcement Learning

2024-12-12 · Songjun Tu, Jingbo Sun, Qichao Zhang, Yaocheng Zhang 외

Offline preference-based reinforcement learning (PbRL) typically operates in two phases: first, use human preferences to learn a reward model and annotate rewards for a reward-free offline dataset; second, learn a policy…

Offline RL

Reinformer: Max-Return Sequence Modeling for Offline RL

2024-05-14 · Zifeng Zhuang, Dengyun Peng, Jinxin Liu, Ziqi Zhang 외

As a data-driven paradigm, offline reinforcement learning (RL) has been formulated as sequence modeling that conditions on the hindsight information including returns, goal or future trajectory. Although promising, this …

D4RLOffline RLReinforcement Learning (RL)

When is Realizability Sufficient for Off-Policy Reinforcement Learning?

2022-11-10 · Andrea Zanette

Model-free algorithms for reinforcement learning typically require a condition called Bellman completeness in order to successfully operate off-policy with function approximation, unless additional conditions are met. Ho…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

Maximum Reward Formulation In Reinforcement Learning

2020-10-08 · Sai Krishna Gottipati, Yashaswi Pathak, Rohan Nuttall, Sahir 외

Reinforcement learning (RL) algorithms typically deal with maximizing the expected cumulative return (discounted or undiscounted, finite or infinite horizon). However, several crucial applications in the real world, such…

Drug Discoveryreinforcement-learningReinforcement LearningReinforcement Learning (RL)