Optimistic Model Rollouts for Pessimistic Offline Policy Optimization
원문 초록
Model-based offline reinforcement learning (RL) has made remarkable progress, offering a promising avenue for improving generalization with synthetic model rollouts. Existing works primarily focus on incorporating pessimism for policy optimization, usually via constructing a Pessimistic Markov Decision Process (P-MDP). However, the P-MDP discourages the policies from learning in out-of-distribution (OOD) regions beyond the support of offline datasets, which can under-utilize the generalization ability of dynamics models. In contrast, we propose constructing an Optimistic MDP (O-MDP). We initially observed the potential benefits of optimism brought by encouraging more OOD rollouts. Motivated by this observation, we present ORPO, a simple yet effective model-based offline RL framework. ORPO generates Optimistic model Rollouts for Pessimistic offline policy Optimization. Specifically, we train an optimistic rollout policy in the O-MDP to sample more OOD model rollouts. Then we relabel the sampled state-action pairs with penalized rewards and optimize the output policy in the P-MDP. Theoretically, we demonstrate that the performance of policies trained with ORPO can be lower-bounded in linear MDPs. Experimental results show that our framework significantly outperforms P-MDP baselines by a margin of 30%, achieving state-of-the-art performance on the widely-used benchmark. Moreover, ORPO exhibits notable advantages in problems that require generalization.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
IRanker: Towards Ranking Foundation Model
Sparse-Reg: Improving Sample Complexity in Offline Reinforcement Learning using Sparsity
DR-SAC: Distributionally Robust Soft Actor-Critic for Reinforcement Learning under Uncertainty
From Novelty to Imitation: Self-Distilled Rewards for Offline Reinforcement Learning
Robust Bandwidth Estimation for Real-Time Communication with Offline Reinforcement Learning
Flow-Based Single-Step Completion for Efficient and Expressive Policy Learning
토론
이 논문과 연결된 포럼 글이 아직 없습니다.