GPU-Parallel Multi-Task Reinforcement Learning with Demonstration Guided Policy Optimization
Large scale GPU-parallel reinforcement learning has changed what can be trained in robot simulation, yet most systems still optimize one specialist policy per task. We propose a construction methodology for turning structured manipulation task families into GPU-parallel multi-task RL benchmarks, and instantiate it as MT-Libero using LIBERO assets and task predicates in Isaac Lab. The resulting benchmark supports simultaneous reinforcement learning over heterogeneous task suites with parallel rendering, physics randomization, and state-input or visual-input policies. To make such training practical under sparse success signals and limited prior data, we further propose DGPO, an on-policy demonstration guided method that combines importance weighted PPO with adaptive behavior cloning on matched demonstration actions. DGPO enables a tunable preference toward demonstrated task distributions, outperforming both prior-free RL and existing demonstration-based methods while preserving the stability and online improvement benefits of on-policy PPO.
Code (0)
등록된 구현이 없습니다.
Tasks
Reinforcement LearningSimilar Papers 제목 키워드 기반
Demonstration-Guided Reinforcement Learning with Learned Skills
Demonstration-guided reinforcement learning (RL) is a promising approach for learning complex behaviors by leveraging both reward feedback and a set of target task demonstrations. Prior approaches for demonstration-guide…
reinforcement-learningReinforcement LearningReinforcement Learning (RL)Robot ManipulationSkill-Critic: Refining Learned Skills for Hierarchical Reinforcement Learning
Hierarchical reinforcement learning (RL) can accelerate long-horizon decision-making by temporally abstracting a policy into multiple levels. Promising results in sparse reward environments have been seen with skills, i.…
Autonomous RacingDecision MakingHierarchical Reinforcement Learningreinforcement-learning+2Demonstration Guided Multi-Objective Reinforcement Learning
Multi-objective reinforcement learning (MORL) is increasingly relevant due to its resemblance to real-world scenarios requiring trade-offs between multiple objectives. Catering to diverse user preferences, traditional re…
Multi-Objective Reinforcement Learningreinforcement-learningReinforcement LearningDemonstration-Guided Continual Reinforcement Learning in Dynamic Environments
Reinforcement learning (RL) excels in various applications but struggles in dynamic environments where the underlying Markov decision process evolves. Continual reinforcement learning (CRL) enables RL agents to continual…
Reinforcement LearningAnyTask: an Automated Task and Data Generation Framework for Advancing Sim-to-Real Policy Learning
Generalist robot learning remains constrained by data: large-scale, diverse, and high-quality interaction data are expensive to collect in the real world. While simulation has become a promising way for scaling up data c…
Reinforcement LearningScene GenerationMotion Planning