Hisao Ishibuchi, Tianye Shu, Ke Shang, Cheng Gong, Yang Nan
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.
For a control problem with multiple conflicting objectives, there exists a set of Pareto-optimal policies called the Pareto set instead of a single optimal policy. When a multi-objective control problem is continuous and complex, traditional multiobjective reinforcement learning (MORL) algorithms search for many Pareto-optimal deep policies to approximate the Pareto set, which is quite resource-consuming. In this paper, we propose a simple and resource-efficient MORL algorithm that learns a continuous representation of the Pareto set in a high-dimensional policy parameter space using a single hypernet. The learned hypernet can directly generate various well-trained policy networks for different user preferences. We compare our method with two state-of-the-art MORL algorithms on seven multi-objective continuous robot control problems. Experimental results show that our method achieves the best overall performance with the least training parameters. An interesting observation is that the Pareto set is well approximated by a curved line or surface in a highdimensional parameter space. This observation will provide insight for researchers to design new MORL algorithms.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2406.18924")
get_code_for_paper("2406.18924")
have("2406.18924")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2406.18924.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2406.18924)
Connect an agent — have() is free.