Text2Reward: Reward Shaping with Language Models for Reinforcement Learning

• URL: http://arxiv.org/abs/2309.11489v3
• Date: Sat, 25 May 2024 06:42:10 GMT
• Title: Text2Reward: Reward Shaping with Language Models for Reinforcement Learning
• Authors: Tianbao Xie, Siheng Zhao, Chen Henry Wu, Yitao Liu, Qian Luo, Victor Zhong, Yanchao Yang, Tao Yu,
• Abstract summary: Text2Reward automates the generation and shaping of dense reward functions based on large language models. It produces interpretable, free-form dense reward codes that cover a wide range of tasks, utilize existing packages, and allow iterative refinement with human feedback. For locomotion tasks, our method learns six novel behaviors with a success rate exceeding 94%.
• Score: 26.95923597947465
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Designing reward functions is a longstanding challenge in reinforcement learning (RL); it requires specialized knowledge or domain data, leading to high costs for development. To address this, we introduce Text2Reward, a data-free framework that automates the generation and shaping of dense reward functions based on large language models (LLMs). Given a goal described in natural language, Text2Reward generates shaped dense reward functions as an executable program grounded in a compact representation of the environment. Unlike inverse RL and recent work that uses LLMs to write sparse reward codes or unshaped dense rewards with a constant function across timesteps, Text2Reward produces interpretable, free-form dense reward codes that cover a wide range of tasks, utilize existing packages, and allow iterative refinement with human feedback. We evaluate Text2Reward on two robotic manipulation benchmarks (ManiSkill2, MetaWorld) and two locomotion environments of MuJoCo. On 13 of the 17 manipulation tasks, policies trained with generated reward codes achieve similar or better task success rates and convergence speed than expert-written reward codes. For locomotion tasks, our method learns six novel locomotion behaviors with a success rate exceeding 94%. Furthermore, we show that the policies trained in the simulator with our method can be deployed in the real world. Finally, Text2Reward further improves the policies by refining their reward functions with human feedback. Video results are available at https://text-to-reward.github.io/ .

Related papers

• On-Robot Reinforcement Learning with Goal-Contrastive Rewards [24.415607337006968]
  Reinforcement Learning (RL) has the potential to enable robots to learn from their own actions in the real world. We propose GCR (Goal-intensiveive Rewards), a dense reward function learning method that can be trained on passive video demonstrations. GCR combines two loss functions, an implicit value loss function that models how the reward increases when traversing a successful trajectory, and a goal-contrastive loss that discriminates between successful and failed trajectories.
  arXiv  Detail & Related papers  (2024-10-25T22:11:54Z)
• Automated Rewards via LLM-Generated Progress Functions [47.50772243693897]
  Large Language Models (LLMs) have the potential to automate reward engineering by leveraging their broad domain knowledge across various tasks. This paper introduces an LLM-driven reward generation framework that is able to produce state-of-the-art policies on the challenging Bi-DexHands benchmark.
  arXiv  Detail & Related papers  (2024-10-11T18:41:15Z)
• Auto MC-Reward: Automated Dense Reward Design with Large Language Models for Minecraft [88.80684763462384]
  This paper introduces an advanced learning system, named Auto MC-Reward, that leverages Large Language Models (LLMs) to automatically design dense reward functions. Experiments demonstrate a significant improvement in the success rate and learning efficiency of our agents in complex tasks in Minecraft.
  arXiv  Detail & Related papers  (2023-12-14T18:58:12Z)
• Reinforcement Learning with Foundation Priors: Let the Embodied Agent Efficiently Learn on Its Own [59.11934130045106]
  We propose Reinforcement Learning with Foundation Priors (RLFP) to utilize guidance and feedback from policy, value, and success-reward foundation models. Within this framework, we introduce the Foundation-guided Actor-Critic (FAC) algorithm, which enables embodied agents to explore more efficiently with automatic reward functions. Our method achieves remarkable performances in various manipulation tasks on both real robots and in simulation.
  arXiv  Detail & Related papers  (2023-10-04T07:56:42Z)
• Language Reward Modulation for Pretraining Reinforcement Learning [61.76572261146311]
  We propose leveraging the capabilities of LRFs as a pretraining signal for reinforcement learning. Our VLM pretraining approach, which is a departure from previous attempts to use LRFs, can warmstart sample-efficient learning on robot manipulation tasks.
  arXiv  Detail & Related papers  (2023-08-23T17:37:51Z)
• Fine-Grained Human Feedback Gives Better Rewards for Language Model Training [108.25635150124539]
  Language models (LMs) often exhibit undesirable text generation behaviors, including generating false, toxic, or irrelevant outputs. We introduce Fine-Grained RLHF, a framework that enables training and learning from reward functions that are fine-grained in two respects.
  arXiv  Detail & Related papers  (2023-06-02T17:11:37Z)
• Reward Design with Language Models [27.24197025688919]
  Reward design in reinforcement learning (RL) is challenging since specifying human notions of desired behavior may be difficult via reward functions or require expert demonstrations. Can we instead cheaply design rewards using a natural language interface? This paper explores how to simplify reward design by prompting a large language model (LLM) such as GPT-3 as a proxy reward function.
  arXiv  Detail & Related papers  (2023-02-27T22:09:35Z)
• Fantastic Rewards and How to Tame Them: A Case Study on Reward Learning for Task-oriented Dialogue Systems [111.80916118530398]
  reinforcement learning (RL) techniques can naturally be utilized to train dialogue strategies to achieve user-specific goals. This paper aims at answering the question of how to efficiently learn and leverage a reward function for training end-to-end (E2E) ToD agents.
  arXiv  Detail & Related papers  (2023-02-20T22:10:04Z)
• Learning to Shape Rewards using a Game of Switching Controls [21.456451774045465]
  We introduce an automated RS framework in which the shaping-reward function is constructed in a novel game between two agents. We prove theoretically that our framework, which easily adopts existing RL algorithms, learns to construct a shaping-reward function that is tailored to the task. We demonstrate the superior performance of our method against state-of-the-art RS algorithms in Cartpole and the challenging console games Gravitar, Solaris and Super Mario.
  arXiv  Detail & Related papers  (2021-03-16T15:56:57Z)
• Reward Machines: Exploiting Reward Function Structure in Reinforcement Learning [22.242379207077217]
  We show how to show the reward function's code to the RL agent so it can exploit the function's internal structure to learn optimal policies. First, we propose reward machines, a type of finite state machine that supports the specification of reward functions. We then describe different methodologies to exploit this structure to support learning, including automated reward shaping, task decomposition, and counterfactual reasoning with off-policy learning.
  arXiv  Detail & Related papers  (2020-10-06T00:10:16Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.