Learning From Symmetry: Meta-reinforcement Learning With Symmetrical Behaviors And Language Instructions

Abstract

Meta-reinforcement learning (meta-RL) is a promising approach that enables the agent to learn new tasks quickly. However, most meta-RL algorithms show poor generalization in multi-task scenarios due to the insufficient task information provided only by rewards. Language-conditioned meta-RL improves the generalization capability by matching language instructions with the agent's behaviors. While both behaviors and language instructions have symmetry, which can speed up human learning of new knowledge. Thus, combining symmetry and language instructions into meta-RL can help improve the algorithm's generalization and learning efficiency. We propose a dual-MDP meta-reinforcement learning method that enables learning new tasks efficiently with symmetrical behaviors and language instructions. We evaluate our method in multiple challenging manipulation tasks, and experimental results show that our method can greatly improve the generalization and learning efficiency of meta-reinforcement lear

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyyao2022learning

Related papers

• Introducing Symmetries To Black Box Meta Reinforcement Learning (2021)0.00
• A Tutorial On Meta-reinforcement Learning (2023)10.85
• MAGE: Meta-reinforcement Learning For Language Agents Toward Strategic Exploration And Exploitation (2026)0.00
• Improving Generalization In Meta Reinforcement Learning Using Learned Objectives (2019)0.00
• HMRL: Hyper-meta Learning For Sparse Reward Reinforcement Learning Problem (2020)0.00
• Model-based Adversarial Meta-reinforcement Learning (2020)0.00
• Learning Action Translator For Meta Reinforcement Learning On Sparse-reward Tasks (2022)4.52
• Guided Meta-policy Search (2019)0.00