Pith

open record

sign in

arxiv: 2506.21782 · v1 · pith:MBW3LIJ5 · submitted 2025-06-26 · cs.LG · cs.RO

M3PO: Massively Multi-Task Model-Based Policy Optimization

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:MBW3LIJ5record.jsonopen to challenge →

classification cs.LG cs.RO
keywords model-basedm3popolicyexplorationmodel-freemulti-taskoptimizationapproaches
0
0 comments X
read the original abstract

We introduce Massively Multi-Task Model-Based Policy Optimization (M3PO), a scalable model-based reinforcement learning (MBRL) framework designed to address sample inefficiency in single-task settings and poor generalization in multi-task domains. Existing model-based approaches like DreamerV3 rely on pixel-level generative models that neglect control-centric representations, while model-free methods such as PPO suffer from high sample complexity and weak exploration. M3PO integrates an implicit world model, trained to predict task outcomes without observation reconstruction, with a hybrid exploration strategy that combines model-based planning and model-free uncertainty-driven bonuses. This eliminates the bias-variance trade-off in prior methods by using discrepancies between model-based and model-free value estimates to guide exploration, while maintaining stable policy updates through a trust-region optimizer. M3PO provides an efficient and robust alternative to existing model-based policy optimization approaches and achieves state-of-the-art performance across multiple benchmarks.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.