mlsanityData to 14 Oct 2026

GEP-PG: Decoupling Exploration and Exploitation in Deep Reinforcement Learning Algorithms

arXiv 1802.05054 ↗First posted 14 Feb 2018cs.LGcited by 40

Not on the map. Why?

Abstract (arXiv)

In continuous action domains, standard deep reinforcement learning algorithms like DDPG suffer from inefficient exploration when facing sparse or deceptive reward problems. Conversely, evolutionary and developmental methods focusing on exploration like Novelty Search, Quality-Diversity or Goal Exploration Processes explore more robustly but are less efficient at fine-tuning policies using gradient descent. In this paper, we present the GEP-PG approach, taking the best of both worlds by sequentially combining a Goal Exploration Process and two variants of DDPG. We study the learning performance of these components and their combination on a low dimensional deceptive reward problem and on the larger Half-Cheetah benchmark. We show that DDPG fails on the former and that GEP-PG improves over the best DDPG variant in both environments. Supplementary videos and discussion can be found at http://frama.link/gep_pg, the code at http://github.com/flowersteam/geppg.

Key facts. Cited by 40 papers in the map (data through 14 Oct 2026). First posted on arXiv 14 Feb 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 9; 2022: 12; 2023: 8; 2024: 7; 2025: 2; 2026: 2.

40 papers.

Sort:

By area:

  1. 2023Guiding Pretraining in Reinforcement Learning with Large Language Modelscited by 187
  2. 2022Exploration in Deep Reinforcement Learning: A Surveycited by 166
  3. 2021A Survey of Exploration Methods in Reinforcement Learningcited by 73
  4. 2021Cooperative Exploration for Multi-Agent Deep Reinforcement Learningcited by 57
  5. 2021Offline Meta-Reinforcement Learning with Online Self-Supervisioncited by 53
  6. 2022Towards a Standardised Performance Evaluation Protocol for Cooperative MARLcited by 49
  7. 2022Approximating Gradients for Differentiable Quality Diversity in Reinforcement Learningcited by 38
  8. 2023Evolutionary Reinforcement Learning: A Surveycited by 29
  9. 2022Combining Evolution and Deep Reinforcement Learning for Policy Search: a Surveycited by 23
  10. 2022Multi-Stage Episodic Control for Strategic Exploration in Text Gamescited by 22
  11. 2022Action Noise in Off-Policy Deep Reinforcement Learning: Impact on Exploration and Performancecited by 22
  12. 2021Semantic Tracklets: An Object-Centric Representation for Visual Multi-Agent Reinforcement Learningcited by 18
28 more
  1. 2021Learn Goal-Conditioned Policy with Intrinsic Motivation for Deep Reinforcement Learningcited by 17
  2. 2021Derivative-Free Reinforcement Learning: A Reviewcited by 15
  3. 2021Sparse Reward Exploration via Novelty Search and Emitterscited by 13
  4. 2023Off-Policy RL Algorithms Can be Sample-Efficient for Continuous Control via Sample Multiple Reusecited by 12
  5. 2022Asking for Knowledge: Training RL Agents to Query External Knowledge Using Languagecited by 10
  6. 2022Evolutionary Action Selection for Gradient-based Policy Learningcited by 7
  7. 2023Improving Deep Policy Gradients with Value Function Searchcited by 7
  8. 2024World Models with Hints of Large Language Models for Goal Achievingcited by 6
  9. 2021Discovering and Exploiting Sparse Rewards in a Learned Behavior Spacecited by 5
  10. 2022Elastic Step DQN: A novel multi-step algorithm to alleviate overestimation in Deep QNetworkscited by 5
  11. 2023Evolving Populations of Diverse RL Agents with MAP-Elitescited by 5
  12. 2023Rethinking Population-assisted Off-policy Reinforcement Learningcited by 5
  13. 2024SPO: Sequential Monte Carlo Policy Optimisationcited by 5
  14. 2024Evolution Guided Generative Flow Networkscited by 4
  15. 2024DynamicPAE: Generating Scene-Aware Physical Adversarial Examples in Real-Timecited by 4
  16. 2022Robots Learn Increasingly Complex Tasks with Intrinsic Motivation and Automatic Curriculum Learningcited by 3
  17. 2024Beyond the Boundaries of Proximal Policy Optimizationcited by 3
  18. 2025Multi-Agent Guided Policy Optimizationcited by 3
  19. 2024ETGL-DDPG: A Deep Deterministic Policy Gradient Algorithm for Sparse Reward Continuous Controlcited by 2
  20. 2021Selection-Expansion: A Unifying Framework for Motion-Planning and Diversity Search Algorithmscited by 1
  21. 2022A Comparative Study of Deep Reinforcement Learning-based Transferable Energy Management Strategies for Hybrid Electric Vehiclescited by 1
  22. 2022A Transferable and Automatic Tuning of Deep Reinforcement Learning for Cost Effective Phishing Detectioncited by 1
  23. 2023Policy Dispersion in Non-Markovian Environmentcited by 0
  24. 2023Supplementing Gradient-Based Reinforcement Learning with Simple Evolutionary Ideascited by 0
  25. 2024MESA: Cooperative Meta-Exploration in Multi-Agent Learning through Exploiting State-Action Space Structurecited by 0
  26. 2025Parameter Estimation using Reinforcement Learning Causal Curiosity: Limits and Challengescited by 0
  27. 2026Characterizing MARL for Energy Control: A Multi-KPI Benchmark on the CityLearn Environmentcited by 0
  28. 2026Grounding Large Language Models in DSGE Simulators for Policy Generation and Forecastingcited by 0