TEACH: Temporal Variance-Driven Curriculum for Reinforcement Learning

2025-12-28 · Gaurav Chaudhary, Laxmidhar Behera arxiv

Reinforcement Learning (RL) has achieved significant success in solving single-goal tasks. However, uniform goal selection often results in sample inefficiency in multi-goal settings where agents must learn a universal goal-conditioned policy. Inspired by the adaptive and structured learning processes observed in biological systems, we propose a novel Student-Teacher learning paradigm with a Temporal Variance-Driven Curriculum to accelerate Goal-Conditioned RL. In this framework, the teacher module dynamically prioritizes goals with the highest temporal variance in the policy's confidence score, parameterized by the state-action value (Q) function. The teacher provides an adaptive and focused learning signal by targeting these high-uncertainty goals, fostering continual and efficient progress. We establish a theoretical connection between the temporal variance of Q-values and the evolution of the policy, providing insights into the method's underlying principles. Our approach is algorithm-agnostic and integrates seamlessly with existing RL frameworks. We demonstrate this through evaluation across 11 diverse robotic manipulation and maze navigation tasks. The results show consistent and notable improvements over state-of-the-art curriculum learning and goal-selection methods.

📄 PDF Abstract BibTeX arXiv:2512.22824

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning

Collaborative Adaptive Curriculum for Progressive Knowledge Distillation

2026-03-19 · Jing Liu, Zhenchao Ma, Han Yu, Bobo Ju 외 arxiv

Recent advances in collaborative knowledge distillation have demonstrated cutting-edge performance for resource-constrained distributed multimedia learning scenarios. However, achieving such competitiveness requires addr…

Knowledge Distillation

Teacher-student curriculum learning for reinforcement learning

2022-10-31 · Yanick Schraner

Reinforcement learning (rl) is a popular paradigm for sequential decision making problems. The past decade's advances in rl have led to breakthroughs in many challenging domains such as video games, board games, robotics…

Board Games Decision Making Deep Reinforcement Learning reinforcement-learning+4

TCOD: Exploring Temporal Curriculum in On-Policy Distillation for Multi-turn Autonomous Agents

2026-04-27 · Jiaqi Wang, Wenhao Zhang, Weijie Shi, Yaliang Li 외 arxiv

On-policy distillation (OPD) has shown strong potential for transferring reasoning ability from frontier or domain-specific models to smaller students. While effective on static single-turn tasks, its behavior in multi-t…

Towards Skilled Population Curriculum for Multi-Agent Reinforcement Learning

2023-02-07 · Rundong Wang, Longtao Zheng, Wei Qiu, Bowei He 외

Recent advances in multi-agent reinforcement learning (MARL) allow agents to coordinate their behaviors in complex environments. However, common MARL algorithms still suffer from scalability and sparse reward issues. One…

Multi-agent Reinforcement Learning reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

DCUR: Data Curriculum for Teaching via Samples with Reinforcement Learning

2021-09-15 · Daniel Seita, Abhinav Gopal, Zhao Mandi, John Canny

Deep reinforcement learning (RL) has shown great empirical successes, but suffers from brittleness and sample inefficiency. A potential remedy is to use a previously-trained policy as a source of supervision. In this wor…

Deep Reinforcement Learning Offline RL reinforcement-learning Reinforcement Learning+1