mlsanityData to 14 Oct 2026

Predicting Future Actions of Reinforcement Learning Agents

arXiv 2410.22459 ↗First posted 29 Oct 2024cs.AIcited by 4

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

Abstract (arXiv)

As reinforcement learning agents become increasingly deployed in real-world scenarios, predicting future agent actions and events during deployment is important for facilitating better human-agent interaction and preventing catastrophic outcomes. This paper experimentally evaluates and compares the effectiveness of future action and event prediction for three types of RL agents: explicitly planning, implicitly planning, and non-planning. We employ two approaches: the inner state approach, which involves predicting based on the inner computations of the agents (e.g., plans or neuron activations), and a simulation-based approach, which involves unrolling the agent in a learned world model. Our results show that the plans of explicitly planning agents are significantly more informative for prediction than the neuron activations of the other types. Furthermore, using internal plans proves more robust to model quality compared to simulation-based approaches when predicting actions, while the results for event prediction are more mixed. These findings highlight the benefits of leveraging inner states and simulations to predict future agent actions and events, thereby improving interaction and safety in real-world deployments.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Placed in Deep RL algorithms and representations, one of 15 directions in Deep reinforcement learning methods. Builds on 16 of its 28 references that are in the map. First posted on arXiv 29 Oct 2024.

Builds on

16 of 28 references.

References · 16

  1. 2017Attention Is All You Needcited by 60,361
  2. 2019Dream to Control: Learning Behaviors by Latent Imaginationcited by 1,653
  3. 2019Mastering Atari, Go, Chess and Shogi by Planning with a Learned Modelcited by 1,353
  4. 2017Constrained Policy Optimizationcited by 983
  5. 2018IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architecturescited by 883
  6. 2017Safe Reinforcement Learning via Shieldingcited by 449
  7. 2019End-to-End Safe Reinforcement Learning through Barrier Functions for Safety-Critical Continuous Control Taskscited by 289
  8. 2018Safe Exploration in Continuous Action Spacescited by 247
  9. 2017Learning with Opponent-Learning Awarenesscited by 222
  10. 2020Recovery RL: Safe Reinforcement Learning with Learned Recovery Zonescited by 175
  11. 2021Goal Misgeneralization in Deep Reinforcement Learningcited by 123
  12. 2016Opponent Modeling in Deep Reinforcement Learningcited by 97
4 more
  1. 2022Safe Reinforcement Learning by Imagining the Near Futurecited by 67
  2. 2018Modeling Others using Oneself in Multi-Agent Reinforcement Learningcited by 66
  3. 2019An investigation of model-free planningcited by 66
  4. 2023Thinker: Learning to Plan and Actcited by 13

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 3; 2026: 1.

4 papers.

  1. 2025Deep RL Needs Deep Behavior Analysis: Exploring Implicit Planning by Model-Free Agents in Open-Ended Environmentscited by 4
  2. 2025Path Channels and Plan Extension Kernels: a Mechanistic Description of Planning in a Sokoban RNNcited by 4
  3. 2025TRACE: A Self-Improving Framework for Robot Behavior Forecasting with Vision-Language Modelscited by 2
  4. 2026Discovering Lattice Reduction Strategies via Self-Playcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026FutureWorld: A Live Reinforcement Learning Environment for Predictive Agents with Real-World Outcome Rewards
  2. 2024Proactive Agent: Shifting LLM Agents from Reactive Responses to Active Assistance
  3. 2026Beyond Prediction: Steering VLM Agents with Retrospective World Modeling
  4. 2026Internalizing the Future: A Unified Agentic Training Paradigm for World Model Planning
  5. 2024Ego-Foresight: Self-supervised Learning of Agent-Aware Representations for Improved RL
  6. 2026Predictive Representations for Skill Transfer in Reinforcement Learning
  7. 2026From Outcomes to Actions: Leveraging Hindsight for Long-Horizon Language Agent Training
  8. 2019Learning to Predict Without Looking Ahead: World Models Without Forward Prediction