Dream and Search to Control: Latent Space Planning for Continuous Control
Learning and planning with latent space dynamics has been shown to be useful for sample efficiency in model-based reinforcement learning (MBRL) for discrete and continuous control tasks. In particular, recent work, for discrete action spaces, demonstrated the effectiveness of latent-space planning via Monte-Carlo Tree Search (MCTS) for bootstrapping MBRL during learning and at test time. However, the potential gains from latent-space tree search have not yet been demonstrated for environments with continuous action spaces. In this work, we propose and explore an MBRL approach for continuous action spaces based on tree-based planning over learned latent dynamics. We show that it is possible to demonstrate the types of bootstrapping benefits as previously shown for discrete spaces. In particular, the approach achieves improved sample efficiency and performance on a majority of challenging continuous-control benchmarks compared to the state-of-the-art.
Code (1)
Tasks
continuous-controlContinuous ControlModel-based Reinforcement LearningReinforcement Learning (RL)Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Discrete Codebook World Models for Continuous Control
In reinforcement learning (RL), world models serve as internal simulators, enabling agents to predict environment dynamics and future outcomes in order to make informed decisions. While previous approaches leveraging dis…
continuous-controlContinuous ControlModel Predictive ControlReinforcement Learning (RL)ELVIS: Ensemble-Calibrated Latent Imagination for Long-Horizon Visual MPC
A central challenge of visual control with model-based reinforcement learning (RL) is reliable long-horizon planning: long rollouts with learned latent dynamics exhibit branching futures and multi-modal action-value dist…
Reinforcement LearningResWM: Residual-Action World Model for Visual RL
Learning predictive world models from raw visual observations is a central challenge in reinforcement learning (RL), especially for robotics and continuous control. Conventional model-based RL frameworks directly conditi…
Reinforcement LearningContinuous ControlMulti-View Dreaming: Multi-View World Model with Contrastive Learning
In this paper, we propose Multi-View Dreaming, a novel reinforcement learning agent for integrated recognition and control from multi-view observations by extending Dreaming. Most current reinforcement learning method as…
Contrastive Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)LithoDreamer: A Physics-Informed World Model for Multi-Stage Computational Lithography
As semiconductor technology nodes scale, computational lithography is essential for ensuring yield and performance. However, lithography is a continuous physical process involving mask optimization, optical imaging, resi…