Sequence Compression Speeds Up Credit Assignment in Reinforcement Learning

• URL: http://arxiv.org/abs/2405.03878v2
• Date: Tue, 4 Jun 2024 05:28:56 GMT
• Title: Sequence Compression Speeds Up Credit Assignment in Reinforcement Learning
• Authors: Aditya A. Ramesh, Kenny Young, Louis Kirsch, Jürgen Schmidhuber,
• Abstract summary: Temporal difference (TD) learning uses bootstrapping to overcome variance but introduces a bias that can only be corrected through many iterations. We propose Chunked-TD, which uses predicted probabilities of transitions from a model for computing $lambda$-return targets.
• Score: 33.28797183140384
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Temporal credit assignment in reinforcement learning is challenging due to delayed and stochastic outcomes. Monte Carlo targets can bridge long delays between action and consequence but lead to high-variance targets due to stochasticity. Temporal difference (TD) learning uses bootstrapping to overcome variance but introduces a bias that can only be corrected through many iterations. TD($\lambda$) provides a mechanism to navigate this bias-variance tradeoff smoothly. Appropriately selecting $\lambda$ can significantly improve performance. Here, we propose Chunked-TD, which uses predicted probabilities of transitions from a model for computing $\lambda$-return targets. Unlike other model-based solutions to credit assignment, Chunked-TD is less vulnerable to model inaccuracies. Our approach is motivated by the principle of history compression and 'chunks' trajectories for conventional TD learning. Chunking with learned world models compresses near-deterministic regions of the environment-policy interaction to speed up credit assignment while still bootstrapping when necessary. We propose algorithms that can be implemented online and show that they solve some problems much faster than conventional TD($\lambda$).

Related papers

• ETS: Efficient Tree Search for Inference-Time Scaling [61.553681244572914]
  One promising approach for test-time compute scaling is search against a process reward model. diversity of trajectories in the tree search process affects the accuracy of the search, since increasing diversity promotes more exploration. We propose Efficient Tree Search (ETS), which promotes KV sharing by pruning redundant trajectories while maintaining necessary diverse trajectories.
  arXiv  Detail & Related papers  (2025-02-19T09:30:38Z)
• Rethinking Token Reduction in MLLMs: Towards a Unified Paradigm for Training-Free Acceleration [31.50005609235654]
  This study rethinks the current landscape of training-free token reduction research. We propose a unified ''filter-correlate-compress'' paradigm that decomposes the token reduction into three distinct stages. Experimental results across 10 benchmarks indicate that our methods can achieve up to an 82.4% reduction in FLOPs.
  arXiv  Detail & Related papers  (2024-11-26T18:53:51Z)
• Time-Scale Separation in Q-Learning: Extending TD($\triangle$) for Action-Value Function Decomposition [0.0]
  This paper introduces Q($Delta$)-Learning, an extension of TD($Delta$) for the Q-Learning framework. TD($Delta$) facilitates efficient learning over several time scales by breaking the Q($Delta$)-function into distinct discount factors. We demonstrate through theoretical analysis and practical evaluations on standard benchmarks like Atari that Q($Delta$)-Learning surpasses conventional Q-Learning and TD learning methods.
  arXiv  Detail & Related papers  (2024-11-21T11:03:07Z)
• Truncated Consistency Models [57.50243901368328]
  Training consistency models requires learning to map all intermediate points along PF ODE trajectories to their corresponding endpoints. We empirically find that this training paradigm limits the one-step generation performance of consistency models. We propose a new parameterization of the consistency function and a two-stage training procedure that prevents the truncated-time training from collapsing to a trivial solution.
  arXiv  Detail & Related papers  (2024-10-18T22:38:08Z)
• RanPAC: Random Projections and Pre-trained Models for Continual Learning [59.07316955610658]
  Continual learning (CL) aims to learn different tasks (such as classification) in a non-stationary data stream without forgetting old ones. We propose a concise and effective approach for CL with pre-trained models.
  arXiv  Detail & Related papers  (2023-07-05T12:49:02Z)
• Consistent Diffusion Models: Mitigating Sampling Drift by Learning to be Consistent [97.64313409741614]
  We propose to enforce a emphconsistency property which states that predictions of the model on its own generated data are consistent across time. We show that our novel training objective yields state-of-the-art results for conditional and unconditional generation in CIFAR-10 and baseline improvements in AFHQ and FFHQ.
  arXiv  Detail & Related papers  (2023-02-17T18:45:04Z)
• Temporal Difference Learning with Compressed Updates: Error-Feedback meets Reinforcement Learning [47.904127007515925]
  We study a variant of the classical temporal difference (TD) learning algorithm with a perturbed update direction. We prove that compressed TD algorithms, coupled with an error-feedback mechanism used widely in optimization, exhibit the same non-asymptotic approximation guarantees as their counterparts. Notably, these are the first finite-time results in RL that account for general compression operators and error-feedback in tandem with linear function approximation and Markovian sampling.
  arXiv  Detail & Related papers  (2023-01-03T04:09:38Z)
• Asynchronous Training Schemes in Distributed Learning with Time Delay [17.259708772713164]
  In the context of distributed deep learning, the issue of stale weights or gradients could result in poor algorithmic performance. In this paper, we propose a different approach to tackle the issue of stale weights or gradients. One practical variant of PC-ASGD is also proposed by adopting a condition to help with the determination of the tradeoff parameter.
  arXiv  Detail & Related papers  (2022-08-28T07:14:59Z)
• ABCinML: Anticipatory Bias Correction in Machine Learning Applications [9.978142416219294]
  We propose an anticipatory dynamic learning approach for correcting the algorithm to mitigate bias before it occurs. Results from experiments over multiple real-world datasets suggest that this approach has promise for anticipatory bias correction.
  arXiv  Detail & Related papers  (2022-06-14T16:26:10Z)
• Distributionally Robust Models with Parametric Likelihood Ratios [123.05074253513935]
  Three simple ideas allow us to train models with DRO using a broader class of parametric likelihood ratios. We find that models trained with the resulting parametric adversaries are consistently more robust to subpopulation shifts when compared to other DRO approaches.
  arXiv  Detail & Related papers  (2022-04-13T12:43:12Z)
• Upper Confidence Primal-Dual Reinforcement Learning for CMDP with Adversarial Loss [145.54544979467872]
  We consider online learning for episodically constrained Markov decision processes (CMDPs) We propose a new emphupper confidence primal-dual algorithm, which only requires the trajectories sampled from the transition model. Our analysis incorporates a new high-probability drift analysis of Lagrange multiplier processes into the celebrated regret analysis of upper confidence reinforcement learning.
  arXiv  Detail & Related papers  (2020-03-02T05:02:23Z)

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.