Reliable Policy Iteration: Performance Robustness Across Architecture and Environment Perturbations

• URL: http://arxiv.org/abs/2512.12088v1
• Date: Fri, 12 Dec 2025 23:33:06 GMT
• Title: Reliable Policy Iteration: Performance Robustness Across Architecture and Environment Perturbations
• Authors: S. R. Eshwar, Aniruddha Mukherjee, Kintan Saha, Krishna Agarwal, Gugan Thoppe, Aditya Gopalan, Gal Dalal,
• Abstract summary: In a recent work, we proposed Reliable Policy Iteration (RPI)<n>RPI restores policy's monotonicity-of-value-estimates property to the function approximation setting.<n>We assess the robustness of RPI's empirical performance on two classical control tasks.
• Score: 11.044907865485056
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: In a recent work, we proposed Reliable Policy Iteration (RPI), that restores policy iteration's monotonicity-of-value-estimates property to the function approximation setting. Here, we assess the robustness of RPI's empirical performance on two classical control tasks -- CartPole and Inverted Pendulum -- under changes to neural network and environmental parameters. Relative to DQN, Double DQN, DDPG, TD3, and PPO, RPI reaches near-optimal performance early and sustains this policy as training proceeds. Because deep RL methods are often hampered by sample inefficiency, training instability, and hyperparameter sensitivity, our results highlight RPI's promise as a more reliable alternative.

Related papers

• Unbiased Dynamic Pruning for Efficient Group-Based Policy Optimization [60.87651283510059]
  Group Relative Policy Optimization (GRPO) effectively scales LLM reasoning but incurs prohibitive computational costs.<n>We propose Dynamic Pruning Policy Optimization (DPPO), a framework that enables dynamic pruning while preserving unbiased gradient estimation.<n>To mitigate the data sparsity induced by pruning, we introduce Dense Prompt Packing, a window-based greedy strategy.
  arXiv  Detail & Related papers  (2026-03-04T14:48:53Z)
• Rethinking the Trust Region in LLM Reinforcement Learning [72.25890308541334]
  Proximal Policy Optimization (PPO) serves as the de facto standard algorithm for Large Language Models (LLMs)<n>We propose Divergence Proximal Policy Optimization (DPPO), which substitutes clipping with a more principled constraint.<n>DPPO achieves superior training and efficiency compared to existing methods, offering a more robust foundation for RL-based fine-tuning.
  arXiv  Detail & Related papers  (2026-02-04T18:59:04Z)
• Behaviour Policy Optimization: Provably Lower Variance Return Estimates for Off-Policy Reinforcement Learning [52.97053840476386]
  We show that well-designed behaviour policies can be used to collect off-policy data for provably lower variance return estimates.<n>We extend this key insight to the online reinforcement learning setting, where both policy evaluation and improvement are interleaved.
  arXiv  Detail & Related papers  (2025-11-13T23:06:40Z)
• BAPO: Stabilizing Off-Policy Reinforcement Learning for LLMs via Balanced Policy Optimization with Adaptive Clipping [69.74252624161652]
  We propose BAlanced Policy Optimization with Adaptive Clipping (BAPO)<n>BAPO dynamically adjusts clipping bounds to adaptively re-balance positive and negative contributions, preserve entropy, and stabilize RL optimization.<n>On AIME 2024 and AIME 2025 benchmarks, our 7B BAPO model surpasses open-source counterparts such as SkyWork-OR1-7B.
  arXiv  Detail & Related papers  (2025-10-21T12:55:04Z)
• Policy Regularized Distributionally Robust Markov Decision Processes with Linear Function Approximation [10.35045003737115]
  Decision-making under distribution shift is a central challenge in reinforcement learning (RL), where training and deployment environments differ.<n>We propose DR-RPO, a model-free online policy optimization method that learns robust policies with sublinear regret.<n>We show that DR-RPO can achieve suboptimality bounds and sample efficiency in robust RL, matching the performance of value-based approaches.
  arXiv  Detail & Related papers  (2025-10-16T02:56:58Z)
• Sampling Complexity of TD and PPO in RKHS [32.00317289826905]
  We revisit Proximal Policy Optimization (PPO) from a function-space perspective.<n>Our results place PPO on a firmer theoretical footing beyond finite-dimensional assumptions.
  arXiv  Detail & Related papers  (2025-09-29T16:19:19Z)
• Relative Entropy Pathwise Policy Optimization [66.03329137921949]
  We present an on-policy algorithm that trains Q-value models purely from on-policy trajectories.<n>We show how to combine policies for exploration with constrained updates for stable training, and evaluate important architectural components that stabilize value function learning.
  arXiv  Detail & Related papers  (2025-07-15T06:24:07Z)
• Monotone and Conservative Policy Iteration Beyond the Tabular Case [11.483050048037752]
  We introduce Reliable Policy Iteration (RPI) and Conservative RPI (CRPI)<n>RPI and CRPI are variants of Policy Iteration (PI) and Conservative PI (CPI)<n>We show that RPI restores the textbook textitmonotonicity of value estimates and that these estimates provably textitlower-bound the true return.
  arXiv  Detail & Related papers  (2025-06-08T13:27:11Z)
• Robust Policy Optimization in Deep Reinforcement Learning [16.999444076456268]
  In continuous action domains, parameterized distribution of action distribution allows easy control of exploration. In particular, we propose an algorithm called Robust Policy Optimization (RPO), which leverages a perturbed distribution. We evaluated our methods on various continuous control tasks from DeepMind Control, OpenAI Gym, Pybullet, and IsaacGym.
  arXiv  Detail & Related papers  (2022-12-14T22:43:56Z)
• Self-supervised Representation Learning with Relative Predictive Coding [102.93854542031396]
  Relative Predictive Coding (RPC) is a new contrastive representation learning objective. RPC maintains a good balance among training stability, minibatch size sensitivity, and downstream task performance. We empirically verify the effectiveness of RPC on benchmark vision and speech self-supervised learning tasks.
  arXiv  Detail & Related papers  (2021-03-21T01:04:24Z)
• Distributional Soft Actor-Critic: Off-Policy Reinforcement Learning for Addressing Value Estimation Errors [13.534873779043478]
  We present a distributional soft actor-critic (DSAC) algorithm to improve the policy performance by mitigating Q-value overestimations. We evaluate DSAC on the suite of MuJoCo continuous control tasks, achieving the state-of-the-art performance.
  arXiv  Detail & Related papers  (2020-01-09T02:27:18Z)

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.