Ping Luo, Bo Yuan, Huazhe Xu, Xueqian Wang, Yao Mu, Guozheng Ma, Zhecheng Yuan, Bo Xia
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
One of the key challenges in visual Reinforcement Learning (RL) is to learn policies that can generalize to unseen environments. Recently, data augmentation techniques aiming at enhancing data diversity have demonstrated proven performance in improving the generalization ability of learned policies. However, due to the sensitivity of RL training, naively applying data augmentation, which transforms each pixel in a task-agnostic manner, may suffer from instability and damage the sample efficiency, thus further exacerbating the generalization performance. At the heart of this phenomenon is the diverged action distribution and high-variance value estimation in the face of augmented images. To alleviate this issue, we propose Task-aware Lipschitz Data Augmentation (TLDA) for visual RL, which explicitly identifies the taskcorrelated pixels with large Lipschitz constants, and only augments the task-irrelevant pixels for stability. We verify the effectiveness of our approach on DeepMind Control suite, CARLA and Deep-Mind Manipulation tasks. The extensive empirical results show that TLDA improves both sample efficiency and generalization; it outperforms previous state-of-the-art methods across 3 different visual control benchmarks.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2202.09982")
get_code_for_paper("2202.09982")
have("2202.09982")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2202.09982.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2202.09982)
Connect an agent — have() is free.