Research map / Multi-agent systems and games / Human-AI and goal-conditioned
Interval timing in deep reinforcement learning agents
Ben Deverett, Ryan Faulkner, Meire Fortunato, Gregory Wayne, Joel Z. Leibo
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use an LSTM controller rather than a feedforward controller | A3C-based interval reproduction agent · Interval reproduction task | accuracy | Improved |
| use an LSTM controller rather than a feedforward controller | A3C-based interval reproduction agent · Untrained sample intervals | generalization | Improved |
| vary the number of controller hidden units from 128 (ablation) | LSTM and feedforward agents · Interval reproduction task | accuracy | No clear effect |
| replace the LSTM with a vanilla RNN (ablation) | Recurrent interval reproduction agent · Interval reproduction task | task learning | Mixed |
| replace the LSTM with a GRU (ablation) | Recurrent interval reproduction agent · Interval reproduction task | task learning | Improved |
| replace the LSTM with an RMC (ablation) | Recurrent interval reproduction agent · Interval reproduction task | task learning | Mixed |
| freeze initially randomized LSTM parameters (ablation) | LSTM interval reproduction agent · Interval reproduction task | accuracy | No clear effect |
| use 10-step chunks for policy and baseline updates instead of 100-step trajectories (ablation) | LSTM interval reproduction agent · Interval reproduction task | accuracy | No clear effect |
| use 10-step chunks for policy and baseline updates instead of 100-step trajectories (ablation) | Feedforward interval reproduction agent · Interval reproduction task | accuracy | Hurt |
Closest papers by meaning
- Deep Reinforcement Learning with Time-Scale Invariant Memory (AAAI 2025 · similarity 0.88)
- Deep RL Needs Deep Behavior Analysis: Exploring Implicit Planning by Model-Free Agents in Open-Ended Environments (NeurIPS 2025 · similarity 0.85)
- Real-Time Reasoning Agents in Evolving Environments (ICLR 2026 · similarity 0.83)
- ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memory (ICLR 2026 · similarity 0.83)
- Episodic Future Thinking Mechanism for Multi-agent Reinforcement Learning (NeurIPS 2024 · similarity 0.83)
- SEEA-R1: Tree-Structured Reinforcement Fine-Tuning for Self-Evolving Embodied Agents (NeurIPS 2025 · similarity 0.83)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
