mlsanityData to 14 Oct 2026

Enhanced Penalty-based Bidirectional Reinforcement Learning Algorithms

arXiv 2504.03163 ↗First posted 4 Apr 2025cs.LGcited by 0

On the map: Deep reinforcement learning methods → Deep RL algorithms and representations

Abstract (arXiv)

This research focuses on enhancing reinforcement learning (RL) algorithms by integrating penalty functions to guide agents in avoiding unwanted actions while optimizing rewards. The goal is to improve the learning process by ensuring that agents learn not only suitable actions but also which actions to avoid. Additionally, we reintroduce a bidirectional learning approach that enables agents to learn from both initial and terminal states, thereby improving speed and robustness in complex environments. Our proposed Penalty-Based Bidirectional methodology is tested against Mani skill benchmark environments, demonstrating an optimality improvement of success rate of approximately 4% compared to existing RL implementations. The findings indicate that this integrated strategy enhances policy learning, adaptability, and overall performance in challenging scenarios

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Deep RL algorithms and representations, one of 15 directions in Deep reinforcement learning methods. Builds on 10 of its 12 references that are in the map. First posted on arXiv 4 Apr 2025.

Builds on

10 of 12 references.

Closest ancestors · 1

Same direction, newest first

  1. 2024Reverse Forward Curriculum Learning for Extreme Sample and Demonstration Efficiency in Reinforcement Learning6 May

Other references · 9

  1. 2017Proximal Policy Optimization Algorithmscited by 15,215
  2. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,885
  3. 2023Diffusion Policy: Visuomotor Policy Learning via Action Diffusioncited by 2,838
  4. 2018Soft Actor-Critic Algorithms and Applicationscited by 1,240
  5. 2023TD-MPC2: Scalable, Robust World Models for Continuous Controlcited by 512
  6. 2023Efficient Online Reinforcement Learning with Offline Datacited by 363
  7. 2023ManiSkill2: A Unified Benchmark for Generalizable Manipulation Skillscited by 327
  8. 2024Principled Penalty-based Methods for Bilevel Reinforcement Learning and RLHFcited by 41
  9. 2019Large-scale Pretraining for Neural Machine Translation with Tens of Billions of Sentence Pairscited by 4

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Improving Online Reinforcement Learning via Bidirectional Behavior Prior Distillation
  2. 2025Incentivizing Safer Actions in Policy Optimization for Constrained Reinforcement Learning
  3. 2025Deterministic Policy Gradient for Reinforcement Learning with Continuous Time and State
  4. 2024Exclusively Penalized Q-learning for Offline Reinforcement Learning
  5. 2024A Comprehensive Survey of Reinforcement Learning: From Algorithms to Practical Challenges
  6. 2024Towards Sample-Efficiency and Generalization of Transfer and Inverse Reinforcement Learning: A Comprehensive Literature Review
  7. 2024Exterior Penalty Policy Optimization with Penalty Metric Network under Constraints
  8. 2024Bridging Evolutionary Algorithms and Reinforcement Learning: A Comprehensive Survey on Hybrid Algorithms