TOP-ERL: Transformer-based Off-Policy Episodic Reinforcement Learning

• URL: http://arxiv.org/abs/2410.09536v1
• Date: Sat, 12 Oct 2024 13:55:26 GMT
• Title: TOP-ERL: Transformer-based Off-Policy Episodic Reinforcement Learning
• Authors: Ge Li, Dong Tian, Hongyi Zhou, Xinkai Jiang, Rudolf Lioutikov, Gerhard Neumann,
• Abstract summary: This work introduces Transformer-based Off-Policy Episodic Reinforcement Learning (TOP-ERL) TOP-ERL is a novel algorithm that enables off-policy updates in the ERL framework.
• Score: 27.93845816476777
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: This work introduces Transformer-based Off-Policy Episodic Reinforcement Learning (TOP-ERL), a novel algorithm that enables off-policy updates in the ERL framework. In ERL, policies predict entire action trajectories over multiple time steps instead of single actions at every time step. These trajectories are typically parameterized by trajectory generators such as Movement Primitives (MP), allowing for smooth and efficient exploration over long horizons while capturing high-level temporal correlations. However, ERL methods are often constrained to on-policy frameworks due to the difficulty of evaluating state-action values for entire action sequences, limiting their sample efficiency and preventing the use of more efficient off-policy architectures. TOP-ERL addresses this shortcoming by segmenting long action sequences and estimating the state-action values for each segment using a transformer-based critic architecture alongside an n-step return estimation. These contributions result in efficient and stable training that is reflected in the empirical results conducted on sophisticated robot learning environments. TOP-ERL significantly outperforms state-of-the-art RL methods. Thorough ablation studies additionally show the impact of key design choices on the model performance.

Related papers

• Q-value Regularized Transformer for Offline Reinforcement Learning [70.13643741130899]
  We propose a Q-value regularized Transformer (QT) to enhance the state-of-the-art in offline reinforcement learning (RL) QT learns an action-value function and integrates a term maximizing action-values into the training loss of Conditional Sequence Modeling (CSM) Empirical evaluations on D4RL benchmark datasets demonstrate the superiority of QT over traditional DP and CSM methods.
  arXiv  Detail & Related papers  (2024-05-27T12:12:39Z)
• Trial and Error: Exploration-Based Trajectory Optimization for LLM Agents [49.85633804913796]
  We present an exploration-based trajectory optimization approach, referred to as ETO. This learning method is designed to enhance the performance of open LLM agents. Our experiments on three complex tasks demonstrate that ETO consistently surpasses baseline performance by a large margin.
  arXiv  Detail & Related papers  (2024-03-04T21:50:29Z)
• Entropy-Regularized Token-Level Policy Optimization for Language Agent Reinforcement [67.1393112206885]
  Large Language Models (LLMs) have shown promise as intelligent agents in interactive decision-making tasks. We introduce Entropy-Regularized Token-level Policy Optimization (ETPO), an entropy-augmented RL method tailored for optimizing LLMs at the token level. We assess the effectiveness of ETPO within a simulated environment that models data science code generation as a series of multi-step interactive tasks.
  arXiv  Detail & Related papers  (2024-02-09T07:45:26Z)
• Open the Black Box: Step-based Policy Updates for Temporally-Correlated Episodic Reinforcement Learning [26.344135827307113]
  We introduce a novel ERL algorithm, Temporally-Correlated Episodic RL (TCE), which effectively utilizes step information in episodic policy updates. TCE achieves comparable performance to recent ERL methods while maintaining data efficiency akin to state-of-the-art (SoTA) step-based RL.
  arXiv  Detail & Related papers  (2024-01-21T09:24:24Z)
• Rethinking Decision Transformer via Hierarchical Reinforcement Learning [54.3596066989024]
  Decision Transformer (DT) is an innovative algorithm leveraging recent advances of the transformer architecture in reinforcement learning (RL) We introduce a general sequence modeling framework for studying sequential decision making through the lens of Hierarchical RL. We show DT emerges as a special case of this framework with certain choices of high-level and low-level policies, and discuss the potential failure of these choices.
  arXiv  Detail & Related papers  (2023-11-01T03:32:13Z)
• Multi-Objective Decision Transformers for Offline Reinforcement Learning [7.386356540208436]
  offline RL is structured to derive policies from static trajectory data without requiring real-time environment interactions. We reformulate offline RL as a multi-objective optimization problem, where prediction is extended to states and returns. Our experiments on D4RL benchmark locomotion tasks reveal that our propositions allow for more effective utilization of the attention mechanism in the transformer model.
  arXiv  Detail & Related papers  (2023-08-31T00:47:58Z)
• ASR: Attention-alike Structural Re-parameterization [53.019657810468026]
  We propose a simple-yet-effective attention-alike structural re- parameterization (ASR) that allows us to achieve SRP for a given network while enjoying the effectiveness of the attention mechanism. In this paper, we conduct extensive experiments from a statistical perspective and discover an interesting phenomenon Stripe Observation, which reveals that channel attention values quickly approach some constant vectors during training.
  arXiv  Detail & Related papers  (2023-04-13T08:52:34Z)
• Backward Imitation and Forward Reinforcement Learning via Bi-directional Model Rollouts [11.4219428942199]
  Traditional model-based reinforcement learning (RL) methods generate forward rollout traces using the learnt dynamics model. In this paper, we propose the backward imitation and forward reinforcement learning (BIFRL) framework. BIFRL empowers the agent to both reach to and explore from high-value states in a more efficient manner.
  arXiv  Detail & Related papers  (2022-08-04T04:04:05Z)
• Enhancing reinforcement learning by a finite reward response filter with a case study in intelligent structural control [0.0]
  In many reinforcement learning (RL) problems, it takes some time until a taken action by the agent reaches its maximum effect on the environment. This paper introduces an applicable enhanced Q-learning method in which at the beginning of the learning phase, the agent takes a single action. We have applied the developed method to a structural control problem in which the goal of the agent is to reduce the vibrations of a building subjected to earthquake excitations with a specified delay.
  arXiv  Detail & Related papers  (2020-10-25T19:28:35Z)
• Discrete Action On-Policy Learning with Action-Value Critic [72.20609919995086]
  Reinforcement learning (RL) in discrete action space is ubiquitous in real-world applications, but its complexity grows exponentially with the action-space dimension. We construct a critic to estimate action-value functions, apply it on correlated actions, and combine these critic estimated action values to control the variance of gradient estimation. These efforts result in a new discrete action on-policy RL algorithm that empirically outperforms related on-policy algorithms relying on variance control techniques.
  arXiv  Detail & Related papers  (2020-02-10T04:23:09Z)

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.