Policy Optimization via Adv2: Adversarial Learning on Advantage Functions

• URL: http://arxiv.org/abs/2310.16473v2
• Date: Mon, 19 May 2025 14:04:48 GMT
• Title: Policy Optimization via Adv2: Adversarial Learning on Advantage Functions
• Authors: Matthieu Jonckheere, Chiara Mignacco, Gilles Stoltz,
• Abstract summary: We revisit the reduction of learning in adversarial Markov decision processes [MDPs] to adversarial learning based on $Q$--values.<n>We discuss the impact of the reduction of learning in adversarial MDPs to adversarial learning in the practical scenarios where transition kernels are unknown.
• Score: 6.793286055326244
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We revisit the reduction of learning in adversarial Markov decision processes [MDPs] to adversarial learning based on $Q$--values; this reduction has been considered in a number of recent articles as one building block to perform policy optimization. Namely, we first consider and extend this reduction in an ideal setting where an oracle provides value functions: it may involve any adversarial learning strategy (not just exponential weights) and it may be based indifferently on $Q$--values or on advantage functions. We then present two extensions: on the one hand, convergence of the last iterate for a vast class of adversarial learning strategies (again, not just exponential weights), satisfying a property called monotonicity of weights; on the other hand, stronger regret criteria for learning in MDPs, inherited from the stronger regret criteria of adversarial learning called strongly adaptive regret and tracking regret. Third, we demonstrate how adversarial learning, also referred to as aggregation of experts, relates to aggregation (orchestration) of expert policies: we obtain stronger forms of performance guarantees in this setting than existing ones, via yet another, simple reduction. Finally, we discuss the impact of the reduction of learning in adversarial MDPs to adversarial learning in the practical scenarios where transition kernels are unknown and value functions must be learned. In particular, we review the literature and note that many strategies for policy optimization feature a policy-improvement step based on exponential weights with estimated $Q$--values. Our main message is that this step may be replaced by the application of any adversarial learning strategy on estimated $Q$--values or on estimated advantage functions. We leave the empirical evaluation of these twists for future research.

Related papers

• RbRL2.0: Integrated Reward and Policy Learning for Rating-based Reinforcement Learning [1.7095639309883044]
  Reinforcement learning (RL) learns policies from various experiences based on the associated cumulative return/rewards without treating them differently.<n>This paper proposes a novel RL method that mimics humans' decision making process by differentiating among collected experiences for effective policy learning.
  arXiv  Detail & Related papers  (2025-01-13T17:19:34Z)
• Towards Effective Evaluations and Comparisons for LLM Unlearning Methods [97.2995389188179]
  This paper seeks to refine the evaluation of machine unlearning for large language models.<n>It addresses two key challenges -- the robustness of evaluation metrics and the trade-offs between competing goals.
  arXiv  Detail & Related papers  (2024-06-13T14:41:00Z)
• Learning Optimal Deterministic Policies with Stochastic Policy Gradients [62.81324245896716]
  Policy gradient (PG) methods are successful approaches to deal with continuous reinforcement learning (RL) problems. In common practice, convergence (hyper)policies are learned only to deploy their deterministic version. We show how to tune the exploration level used for learning to optimize the trade-off between the sample complexity and the performance of the deployed deterministic policy.
  arXiv  Detail & Related papers  (2024-05-03T16:45:15Z)
• Handling Cost and Constraints with Off-Policy Deep Reinforcement Learning [2.793095554369282]
  Most popular methods for off-policy learning include policy improvement steps where a learned state-action ($Q$) value function is maximized over selected batches of data. We revisit this strategy in environments with "mixed-sign" reward functions. We find that this second approach, when applied to continuous action spaces with mixed-sign rewards, consistently and significantly outperforms state-of-the-art methods augmented by resetting.
  arXiv  Detail & Related papers  (2023-11-30T16:31:04Z)
• Adversarial Batch Inverse Reinforcement Learning: Learn to Reward from Imperfect Demonstration for Interactive Recommendation [23.048841953423846]
  We focus on the problem of learning to reward, which is fundamental to reinforcement learning. Previous approaches either introduce additional procedures for learning to reward, thereby increasing the complexity of optimization. We propose a novel batch inverse reinforcement learning paradigm that achieves the desired properties.
  arXiv  Detail & Related papers  (2023-10-30T13:43:20Z)
• Hierarchical Decomposition of Prompt-Based Continual Learning: Rethinking Obscured Sub-optimality [55.88910947643436]
  Self-supervised pre-training is essential for handling vast quantities of unlabeled data in practice. HiDe-Prompt is an innovative approach that explicitly optimize the hierarchical components with an ensemble of task-specific prompts and statistics. Our experiments demonstrate the superior performance of HiDe-Prompt and its robustness to pre-training paradigms in continual learning.
  arXiv  Detail & Related papers  (2023-10-11T06:51:46Z)
• Consciousness-Inspired Spatio-Temporal Abstractions for Better Generalization in Reinforcement Learning [83.41487567765871]
  Skipper is a model-based reinforcement learning framework. It automatically generalizes the task given into smaller, more manageable subtasks. It enables sparse decision-making and focused abstractions on the relevant parts of the environment.
  arXiv  Detail & Related papers  (2023-09-30T02:25:18Z)
• Provable Guarantees for Generative Behavior Cloning: Bridging Low-Level Stability and High-Level Behavior [51.60683890503293]
  We propose a theoretical framework for studying behavior cloning of complex expert demonstrations using generative modeling. We show that pure supervised cloning can generate trajectories matching the per-time step distribution of arbitrary expert trajectories.
  arXiv  Detail & Related papers  (2023-07-27T04:27:26Z)
• Understanding and Constructing Latent Modality Structures in Multi-modal Representation Learning [53.68371566336254]
  We argue that the key to better performance lies in meaningful latent modality structures instead of perfect modality alignment. Specifically, we design 1) a deep feature separation loss for intra-modality regularization; 2) a Brownian-bridge loss for inter-modality regularization; and 3) a geometric consistency loss for both intra- and inter-modality regularization.
  arXiv  Detail & Related papers  (2023-03-10T14:38:49Z)
• Performative Reinforcement Learning [8.07595093287034]
  We introduce the concept of performatively stable policy. We show that repeatedly optimizing this objective converges to a performatively stable policy.
  arXiv  Detail & Related papers  (2022-06-30T18:26:03Z)
• On the Complexity of Adversarial Decision Making [101.14158787665252]
  We show that the Decision-Estimation Coefficient is necessary and sufficient to obtain low regret for adversarial decision making. We provide new structural results that connect the Decision-Estimation Coefficient to variants of other well-known complexity measures.
  arXiv  Detail & Related papers  (2022-06-27T06:20:37Z)
• Imitating, Fast and Slow: Robust learning from demonstrations via decision-time planning [96.72185761508668]
  Planning at Test-time (IMPLANT) is a new meta-algorithm for imitation learning. We demonstrate that IMPLANT significantly outperforms benchmark imitation learning approaches on standard control environments.
  arXiv  Detail & Related papers  (2022-04-07T17:16:52Z)
• Explaining, Evaluating and Enhancing Neural Networks' Learned Representations [2.1485350418225244]
  We show how explainability can be an aid, rather than an obstacle, towards better and more efficient representations. We employ such attributions to define two novel scores for evaluating the informativeness and the disentanglement of latent embeddings. We show that adopting our proposed scores as constraints during the training of a representation learning task improves the downstream performance of the model.
  arXiv  Detail & Related papers  (2022-02-18T19:00:01Z)
• Offline Reinforcement Learning with Implicit Q-Learning [85.62618088890787]
  Current offline reinforcement learning methods need to query the value of unseen actions during training to improve the policy. We propose an offline RL method that never needs to evaluate actions outside of the dataset. This method enables the learned policy to improve substantially over the best behavior in the data through generalization.
  arXiv  Detail & Related papers  (2021-10-12T17:05:05Z)
• Learning Pessimism for Robust and Efficient Off-Policy Reinforcement Learning [0.0]
  Off-policy deep reinforcement learning algorithms compensate for overestimation bias during temporal-difference learning. In this work, we propose a novel learnable penalty to enact such pessimism. We also propose to learn the penalty alongside the critic with dual TD-learning, a strategy to estimate and minimize the bias magnitude in the target returns.
  arXiv  Detail & Related papers  (2021-10-07T12:13:19Z)
• Learning with Multiclass AUC: Theory and Algorithms [141.63211412386283]
  Area under the ROC curve (AUC) is a well-known ranking metric for problems such as imbalanced learning and recommender systems. In this paper, we start an early trial to consider the problem of learning multiclass scoring functions via optimizing multiclass AUC metrics.
  arXiv  Detail & Related papers  (2021-07-28T05:18:10Z)
• Taylor Expansion of Discount Factors [56.46324239692532]
  In practical reinforcement learning (RL), the discount factor used for estimating value functions often differs from that used for defining the evaluation objective. In this work, we study the effect that this discrepancy of discount factors has during learning, and discover a family of objectives that interpolate value functions of two distinct discount factors.
  arXiv  Detail & Related papers  (2021-06-11T05:02:17Z)
• State Augmented Constrained Reinforcement Learning: Overcoming the Limitations of Learning with Rewards [88.30521204048551]
  A common formulation of constrained reinforcement learning involves multiple rewards that must individually accumulate to given thresholds. We show a simple example in which the desired optimal policy cannot be induced by any weighted linear combination of rewards. This work addresses this shortcoming by augmenting the state with Lagrange multipliers and reinterpreting primal-dual methods.
  arXiv  Detail & Related papers  (2021-02-23T21:07:35Z)
• Adaptive Approximate Policy Iteration [22.915651391812187]
  We present a learning scheme which enjoys a $tildeO(T2/3)$ regret bound for undiscounted, continuing learning in uniformly ergodic MDPs. This is an improvement over the best existing bound of $tildeO(T3/4)$ for the average-reward case with function approximation.
  arXiv  Detail & Related papers  (2020-02-08T02:27:03Z)

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.