Generalized Back-Stepping Experience Replay in Sparse-Reward Environments
On the map: Deep reinforcement learning methods → Deep RL algorithms and representations
Abstract (arXiv)
Back-stepping experience replay (BER) is a reinforcement learning technique that can accelerate learning efficiency in reversible environments. BER trains an agent with generated back-stepping transitions of collected experiences and normal forward transitions. However, the original algorithm is designed for a dense-reward environment that does not require complex exploration, limiting the BER technique to demonstrate its full potential. Herein, we propose an enhanced version of BER called Generalized BER (GBER), which extends the original algorithm to sparse-reward environments, particularly those with complex structures that require the agent to explore. GBER improves the performance of BER by introducing relabeling mechanism and applying diverse sampling strategies. We evaluate our modified version, which is based on a goal-conditioned deep deterministic policy gradient offline learning algorithm, across various maze navigation environments. The experimental results indicate that the GBER algorithm can significantly boost the performance and stability of the baseline algorithm in various sparse-reward environments, especially those with highly structural symmetricity.
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. First posted on arXiv 20 Dec 2024.
Builds on
0 of 0 references.
No references here yet.
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2024A Tighter Convergence Proof of Reverse Experience Replay
- 2024Back-stepping Experience Replay with Application to Model-free Reinforcement Learning for a Soft Snake Robot
- 2024CUER: Corrected Uniform Experience Replay for Off-Policy Continuous Deep Reinforcement Learning Algorithms
- 2024Efficient Diversity-based Experience Replay for Deep Reinforcement Learning
- 2025Enhancing Deep Deterministic Policy Gradients on Continuous Control Tasks with Decoupled Prioritized Experience Replay
- 2025GCHR : Goal-Conditioned Hindsight Regularization for Sample-Efficient Reinforcement Learning
- 2026Variance Reduction Based Experience Replay for Policy Optimization
- 2025Adaptable Hindsight Experience Replay for Search-Based Learning