Research map / Multi-agent systems and games / Human-AI and goal-conditioned
Non-exponential Reward Discounting in Reinforcement Learning
Raja Farrukh Ali
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 hyperbolic discounting-based advantage estimation to learn over multiple horizons | Policy-gradient methods · Procedurally generated environments | performance | Improved |
| Learn over multiple horizons without specifying the behavior policy through the discounting function | Off-policy, value-based methods · Procedurally generated environments | performance | No clear effect |
| Choose the behavior policy through the discounting function, hyperbolic or exponential | Off-policy, value-based methods · Procedurally generated environments | performance | Mixed |
Closest papers by meaning
- Reinforcement Learning with Non-Exponential Discounting (NeurIPS 2022 · similarity 0.93)
- Beyond the Bellman Recursion: A Pontryagin-Guided Framework for Non-Exponential Discounting (ICML 2026 · similarity 0.87)
- Partial Identifiability in Inverse Reinforcement Learning for Agents with Non-Exponential Discounting (AAAI 2025 · similarity 0.87)
- A Continuous-time Tractable Model for Present-biased Agents (AAAI 2025 · similarity 0.86)
- Beyond Optimism: Exploration With Partially Observable Rewards (NeurIPS 2024 · similarity 0.84)
- Catastrophic Goodhart: regularizing RLHF with KL divergence does not mitigate heavy-tailed reward misspecification (NeurIPS 2024 · similarity 0.84)
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.
