Boosting Reinforcement Learning with Strongly Delayed Feedback Through Auxiliary Short Delays

• URL: http://arxiv.org/abs/2402.03141v2
• Date: Wed, 5 Jun 2024 19:12:37 GMT
• Title: Boosting Reinforcement Learning with Strongly Delayed Feedback Through Auxiliary Short Delays
• Authors: Qingyuan Wu, Simon Sinong Zhan, Yixuan Wang, Yuhui Wang, Chung-Wei Lin, Chen Lv, Qi Zhu, Jürgen Schmidhuber, Chao Huang,
• Abstract summary: Reinforcement learning (RL) is challenging in the common case of delays between events and their sensory perceptions. We present a novel Auxiliary-Delayed Reinforcement Learning (AD-RL) method that leverages auxiliary tasks involving short delays to accelerate RL with long delays. Specifically, AD-RL learns a value function for short delays and uses bootstrapping and policy improvement techniques to adjust it for long delays.
• Score: 41.52768902667611
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Reinforcement learning (RL) is challenging in the common case of delays between events and their sensory perceptions. State-of-the-art (SOTA) state augmentation techniques either suffer from state space explosion or performance degeneration in stochastic environments. To address these challenges, we present a novel Auxiliary-Delayed Reinforcement Learning (AD-RL) method that leverages auxiliary tasks involving short delays to accelerate RL with long delays, without compromising performance in stochastic environments. Specifically, AD-RL learns a value function for short delays and uses bootstrapping and policy improvement techniques to adjust it for long delays. We theoretically show that this can greatly reduce the sample complexity. On deterministic and stochastic benchmarks, our method significantly outperforms the SOTAs in both sample efficiency and policy performance. Code is available at https://github.com/QingyuanWuNothing/AD-RL.

Related papers

• DEER: A Delay-Resilient Framework for Reinforcement Learning with Variable Delays [26.032139258562708]
  We propose $textbfDEER (Delay-resilient-Enhanced RL)$, a framework designed to effectively enhance the interpretability and address the random delay issues. In a variety of delayed scenarios, the trained encoder can seamlessly integrate with standard RL algorithms without requiring additional modifications. The results confirm that DEER is superior to state-of-the-art RL algorithms in both constant and random delay settings.
  arXiv  Detail & Related papers  (2024-06-05T09:45:26Z)
• Variational Delayed Policy Optimization [25.668512485348952]
  In environments with delayed observation, state augmentation by including actions within the delay window is adopted to retrieve Markovian property to enable reinforcement learning (RL) State-of-the-art (SOTA) RL techniques with Temporal-Difference (TD) learning frameworks often suffer from learning inefficiency, due to the significant expansion of the augmented state space with the delay. This work introduces a novel framework called Variational Delayed Policy Optimization (VDPO), which reformulates delayed RL as a variational inference problem.
  arXiv  Detail & Related papers  (2024-05-23T06:57:04Z)
• Solving Continual Offline Reinforcement Learning with Decision Transformer [78.59473797783673]
  Continuous offline reinforcement learning (CORL) combines continuous and offline reinforcement learning. Existing methods, employing Actor-Critic structures and experience replay (ER), suffer from distribution shifts, low efficiency, and weak knowledge-sharing. We introduce multi-head DT (MH-DT) and low-rank adaptation DT (LoRA-DT) to mitigate DT's forgetting problem.
  arXiv  Detail & Related papers  (2024-01-16T16:28:32Z)
• Posterior Sampling with Delayed Feedback for Reinforcement Learning with Linear Function Approximation [62.969796245827006]
  Delayed-PSVI is an optimistic value-based algorithm that explores the value function space via noise perturbation with posterior sampling. We show our algorithm achieves $widetildeO(sqrtd3H3 T + d2H2 E[tau]$ worst-case regret in the presence of unknown delays. We incorporate a gradient-based approximate sampling scheme via Langevin dynamics for Delayed-LPSVI.
  arXiv  Detail & Related papers  (2023-10-29T06:12:43Z)
• Action-Quantized Offline Reinforcement Learning for Robotic Skill Learning [68.16998247593209]
  offline reinforcement learning (RL) paradigm provides recipe to convert static behavior datasets into policies that can perform better than the policy that collected the data. In this paper, we propose an adaptive scheme for action quantization. We show that several state-of-the-art offline RL methods such as IQL, CQL, and BRAC improve in performance on benchmarks when combined with our proposed discretization scheme.
  arXiv  Detail & Related papers  (2023-10-18T06:07:10Z)
• Reasoning with Latent Diffusion in Offline Reinforcement Learning [11.349356866928547]
  offline reinforcement learning holds promise as a means to learn high-reward policies from a static dataset. Key challenge in offline RL lies in effectively stitching portions of suboptimal trajectories from the static dataset. We propose a novel approach that leverages the expressiveness of latent diffusion to model in-support trajectory sequences as compressed latent skills.
  arXiv  Detail & Related papers  (2023-09-12T20:58:21Z)
• FIRE: A Failure-Adaptive Reinforcement Learning Framework for Edge Computing Migrations [52.85536740465277]
  FIRE is a framework that adapts to rare events by training a RL policy in an edge computing digital twin environment. We propose ImRE, an importance sampling-based Q-learning algorithm, which samples rare events proportionally to their impact on the value function. We show that FIRE reduces costs compared to vanilla RL and the greedy baseline in the event of failures.
  arXiv  Detail & Related papers  (2022-09-28T19:49:39Z)
• Revisiting State Augmentation methods for Reinforcement Learning with Stochastic Delays [10.484851004093919]
  This paper formally describes the notion of Markov Decision Processes (MDPs) with delays. We show that delayed MDPs can be transformed into equivalent standard MDPs (without delays) with significantly simplified cost structure. We employ this equivalence to derive a model-free Delay-Resolved RL framework and show that even a simple RL algorithm built upon this framework achieves near-optimal rewards in environments with delays in actions and observations.
  arXiv  Detail & Related papers  (2021-08-17T10:45:55Z)
• Reinforcement Learning with Random Delays [14.707955337702943]
  We show that partially resampling trajectory fragments in hindsight allows for off-policy multi-step value estimation. We apply this principle to derive Delay-Correcting Actor-Critic (DCAC), an algorithm based on Soft Actor-Critic with significantly better performance in environments with delays.
  arXiv  Detail & Related papers  (2020-10-06T18:39:23Z)
• Robust Deep Reinforcement Learning through Adversarial Loss [74.20501663956604]
  Recent studies have shown that deep reinforcement learning agents are vulnerable to small adversarial perturbations on the agent's inputs. We propose RADIAL-RL, a principled framework to train reinforcement learning agents with improved robustness against adversarial attacks.
  arXiv  Detail & Related papers  (2020-08-05T07:49:42Z)

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.