Backward Curriculum Reinforcement Learning

2022-12-29 · KyungMin Ko

Current reinforcement learning algorithms train an agent using forward-generated trajectories, which provide little guidance so that the agent can explore as much as possible. While realizing the value of reinforcement learning results from sufficient exploration, this approach leads to a trade-off in losing sample efficiency, an essential factor impacting algorithm performance. Previous tasks use reward-shaping techniques and network structure modification to increase sample efficiency. However, these methods require many steps to implement. In this work, we propose novel backward curriculum reinforcement learning that begins training the agent using the backward trajectory of the episode instead of the original forward trajectory. This approach provides the agent with a strong reward signal, enabling more sample-efficient learning. Moreover, our method only requires a minor change in the algorithm of reversing the order of the trajectory before agent training, allowing a straightforward application to any state-of-the-art algorithm.

📄 PDF Abstract BibTeX arXiv:2212.14214

Code (0)

등록된 구현이 없습니다.

Tasks

reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

BaRC: Backward Reachability Curriculum for Robotic Reinforcement Learning

2018-06-16 · Boris Ivanovic, James Harrison, Apoorva Sharma, Mo Chen 외

Model-free Reinforcement Learning (RL) offers an attractive approach to learn control policies for high-dimensional systems, but its relatively poor sample complexity often forces training in simulated environments. Even…

continuous-control Continuous Control reinforcement-learning Reinforcement Learning+1

Feudal Reinforcement Learning by Reading Manuals

2021-10-13 · Kai Wang, Zhonghao Wang, Mo Yu, Humphrey Shi

Reading to act is a prevalent but challenging task which requires the ability to reason from a concise instruction. However, previous works face the semantic mismatch between the low-level actions and the high-level lang…

reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Backplay: "Man muss immer umkehren"

2018-07-18 · Cinjon Resnick, Roberta Raileanu, Sanyam Kapoor, Alexander Peysakhovich 외

Model-free reinforcement learning (RL) requires a large number of trials to learn a good policy, especially in environments with sparse rewards. We explore a method to improve the sample efficiency when we have access to…

Reinforcement Learning Reinforcement Learning (RL)

Backplay: 'Man muss immer umkehren'

2019-05-01 · ICLR 2019 5 · Cinjon Resnick, Roberta Raileanu, Sanyam Kapoor, Alexander Peysakhovich 외

Reinforcement Learning Reinforcement Learning (RL)

Omni-Thinker: Scaling Multi-Task RL in LLMs with Hybrid Reward and Task Scheduling

2025-07-20 · Derek Li, Jiaming Zhou, Leo Maxime Brunswic, Abbas Ghaddar 외 arxiv

The pursuit of general-purpose artificial intelligence depends on large language models (LLMs) that can handle both structured reasoning and open-ended generation. We present Omni-Thinker, a unified reinforcement learnin…

Reinforcement Learning