SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2403.13578 · 2024

Dynamic Reward Adjustment in Multi-Reward Reinforcement Learning for Counselor Reflection Generation

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 2 functions out of this paper's own repositories and ran 1 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
michigannlp/dynaopt canonical 1 of 2
FunctionStatusWhere it lives
to_vw_example_format Ran michigannlp/dynaopt/con_rl_train.py
code served (permissive licence) · get_code("d68fe00f92e5fbb7")
sample_custom_pmf Not yet run michigannlp/dynaopt/con_rl_train.py
code served (permissive licence) · get_code("7f9d7f4332331eda")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

In this paper, we study the problem of multi-reward reinforcement learning to jointly optimize for multiple text qualities for natural language generation. We focus on the task of counselor reflection generation, where we optimize the generators to simultaneously improve the fluency, coherence, and reflection quality of generated counselor responses. We introduce two novel bandit methods, DynaOpt and C-DynaOpt, which rely on the broad strategy of combining rewards into a single value and optimizing them simultaneously. Specifically, we employ non-contextual and contextual multi-arm bandits to dynamically adjust multiple reward weights during training. Through automatic and manual evaluations, we show that our proposed techniques, DynaOpt and C-DynaOpt, outperform existing naive and bandit baselines, showcasing their potential for enhancing language models.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2403.13578")
get_code_for_paper("2403.13578")
have("2403.13578")

Connect an agent — have() is free.