Match or Replay: Self Imitating Proximal Policy Optimization

• URL: http://arxiv.org/abs/2603.27515v1
• Date: Sun, 29 Mar 2026 04:44:48 GMT
• Title: Match or Replay: Self Imitating Proximal Policy Optimization
• Abstract summary: Reinforcement Learning (RL) agents often struggle with inefficient exploration.<n>Traditional exploration strategies can lead to slow learning and suboptimal performance.<n>We propose a self-imitating on-policy algorithm that enhances exploration and sample efficiency.
• Score: 14.033176618356746
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Reinforcement Learning (RL) agents often struggle with inefficient exploration, particularly in environments with sparse rewards. Traditional exploration strategies can lead to slow learning and suboptimal performance because agents fail to systematically build on previously successful experiences, thereby reducing sample efficiency. To tackle this issue, we propose a self-imitating on-policy algorithm that enhances exploration and sample efficiency by leveraging past high-reward state-action pairs to guide policy updates. Our method incorporates self-imitation by using optimal transport distance in dense reward environments to prioritize state visitation distributions that match the most rewarding trajectory. In sparse-reward environments, we uniformly replay successful self-encountered trajectories to facilitate structured exploration. Experimental results across diverse environments demonstrate substantial improvements in learning efficiency, including MuJoCo for dense rewards and the partially observable 3D Animal-AI Olympics and multi-goal PointMaze for sparse rewards. Our approach achieves faster convergence and significantly higher success rates compared to state-of-the-art self-imitating RL baselines. These findings underscore the potential of self-imitation as a robust strategy for enhancing exploration in RL, with applicability to more complex tasks.

Related papers

• RSPO: Reward-Swap Policy Optimization for Multi-Turn LLM Agents [24.215311212134882]
  We propose Reward-Swap Policy Optimization (RSPO) to leverage the rich information from dense process rewards to facilitate training with outcome rewards.<n>RSPO ensures the diversity of sampled trajectories while guaranteeing consistency between the optimization objective and the true outcome rewards.
  arXiv  Detail & Related papers  (2026-07-06T06:32:39Z)
• Learning Process Rewards via Success Visitation Matching for Efficient RL [54.67547527674048]
  We propose a simple approach to transform a sparse outcome reward into a dense process reward.<n>Our approach relies on training a discriminator to distinguish between previous successful and unsuccessful episodes.<n>By incentivizing the policy to match the visitations over all states, not just those that correspond to task success, this reward provides dense feedback on whether progress is being made towards task completion.
  arXiv  Detail & Related papers  (2026-06-22T17:30:24Z)
• Towards better dense rewards in Reinforcement Learning Applications [0.7344790292816897]
  Finding meaningful and accurate dense rewards is a fundamental task in the field of reinforcement learning (RL)<n>Dense reward functions offer a potential solution by shaping agent behavior and accelerating learning.<n>This proposal explores several approaches to dealing with unsolved problems and enhancing the effectiveness and reliability of dense reward construction.
  arXiv  Detail & Related papers  (2025-12-03T22:36:55Z)
• Agentic Reinforcement Learning with Implicit Step Rewards [92.26560379363492]
  Large language models (LLMs) are increasingly developed as autonomous agents using reinforcement learning (agentic RL)<n>We introduce implicit step rewards for agentic RL (iStar), a general credit-assignment strategy that integrates seamlessly with standard RL algorithms.<n>We evaluate our method on three challenging agent benchmarks, including WebShop and VisualSokoban, as well as open-ended social interactions with unverifiable rewards in SOTOPIA.
  arXiv  Detail & Related papers  (2025-09-23T16:15:42Z)
• Random Latent Exploration for Deep Reinforcement Learning [71.88709402926415]
  We introduce Random Latent Exploration (RLE), a simple yet effective exploration strategy in reinforcement learning (RL)<n>On average, RLE outperforms noise-based methods, which perturb the agent's actions, and bonus-based exploration, which rewards the agent for attempting novel behaviors.<n>RLE is as simple as noise-based methods, as it avoids complex bonus calculations but retains the deep exploration benefits of bonus-based methods.
  arXiv  Detail & Related papers  (2024-07-18T17:55:22Z)
• 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)
• Policy Optimization with Smooth Guidance Learned from State-Only Demonstrations [2.709826237514737]
  The sparsity of reward feedback remains a challenging problem in online deep reinforcement learning. We propose a simple and efficient algorithm called Policy Optimization with Smooth Guidance (POSG) We show POSG's significant advantages in control performance and convergence speed in four sparse-reward environments.
  arXiv  Detail & Related papers  (2023-12-30T07:41:45Z)
• Efficient Reinforcement Learning via Decoupling Exploration and Utilization [6.305976803910899]
  Reinforcement Learning (RL) has achieved remarkable success across multiple fields and applications, including gaming, robotics, and autonomous vehicles. In this work, our aim is to train agent with efficient learning by decoupling exploration and utilization, so that agent can escaping the conundrum of suboptimal Solutions. The above idea is implemented in the proposed OPARL (Optimistic and Pessimistic Actor Reinforcement Learning) algorithm.
  arXiv  Detail & Related papers  (2023-12-26T09:03:23Z)
• Symmetric Replay Training: Enhancing Sample Efficiency in Deep Reinforcement Learning for Combinatorial Optimization [42.92248233465095]
  We propose a simple but effective method, called symmetric replay training (SRT), which can be easily integrated into various Deep reinforcement learning (DRL) methods. Our method leverages high-reward samples to encourage exploration of symmetric regions without additional online interactions - free. Experimental results demonstrate the consistent improvement of our method in sample efficiency across diverse DRL methods applied to real-world tasks.
  arXiv  Detail & Related papers  (2023-06-02T05:34:01Z)
• Basis for Intentions: Efficient Inverse Reinforcement Learning using Past Experience [89.30876995059168]
  inverse reinforcement learning (IRL) -- inferring the reward function of an agent from observing its behavior. This paper addresses the problem of IRL -- inferring the reward function of an agent from observing its behavior.
  arXiv  Detail & Related papers  (2022-08-09T17:29:49Z)
• Reward Uncertainty for Exploration in Preference-based Reinforcement Learning [88.34958680436552]
  We present an exploration method specifically for preference-based reinforcement learning algorithms. Our main idea is to design an intrinsic reward by measuring the novelty based on learned reward. Our experiments show that exploration bonus from uncertainty in learned reward improves both feedback- and sample-efficiency of preference-based RL algorithms.
  arXiv  Detail & Related papers  (2022-05-24T23:22:10Z)
• Hindsight Task Relabelling: Experience Replay for Sparse Reward Meta-RL [91.26538493552817]
  We present a formulation of hindsight relabeling for meta-RL, which relabels experience during meta-training to enable learning to learn entirely using sparse reward. We demonstrate the effectiveness of our approach on a suite of challenging sparse reward goal-reaching environments.
  arXiv  Detail & Related papers  (2021-12-02T00:51:17Z)

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.