Thomy Phan, Fabian Ritz, Philipp Altmann, Jonas Üßlein, Claudia Linnhoff-Popien, Leonard Feuchtinger
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.
The safe application of reinforcement learning (RL) requires generalization from limited training data to unseen scenarios. Yet, fulfilling tasks under changing circumstances is a key challenge in RL. Current state-of-the-art approaches for generalization apply data augmentation techniques to increase the diversity of training data. Even though this prevents overfitting to the training environment(s), it hinders policy optimization. Crafting a suitable observation, only containing crucial information, has been shown to be a challenging task itself. To improve data efficiency and generalization capabilities, we propose Compact Reshaped Observation Processing (CROP) to reduce the state information used for policy optimization. By providing only relevant information, overfitting to a specific training layout is precluded and generalization to unseen environments is improved. We formulate three CROPs that can be applied to fully observable observation-and action-spaces and provide methodical foundation. We empirically show the improvements of CROP in a distributionally shifted safety gridworld. We furthermore provide benchmark comparisons to full observability and data-augmentation in two different-sized procedurally generated mazes.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2304.13616")
get_code_for_paper("2304.13616")
have("2304.13616")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2304.13616.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2304.13616)
Connect an agent — have() is free.