Research map / Reinforcement learning / Visual and representation RL
On Learning Intrinsic Rewards for Policy Gradient Methods
Zeyu Zheng, Junhyuk Oh, Satinder Singh
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 |
|---|---|---|---|
| Add LIRPG-learned intrinsic rewards to A2C | A2C · 15 Atari games | human-normalized score improvement | Improved |
| Add LIRPG-learned intrinsic rewards instead of a constant live bonus | A2C · 15 Atari games | human-normalized score improvement | Mixed |
| Add LIRPG-learned intrinsic rewards to PPO | PPO · Delayed MuJoCo, delay 20 | average reward | Mixed |
| Add LIRPG-learned intrinsic rewards instead of a constant live bonus | PPO · Delayed MuJoCo, delay 20 | average reward | Mixed |
| Train the policy using only learned intrinsic rewards rather than a mixture of intrinsic and extrinsic rewards (ablation) | PPO+LIRPG · MuJoCo | average reward | Mixed |
Closest papers by meaning
- What Can Learned Intrinsic Rewards Capture? (ICML 2020 · similarity 0.90)
- Behavior Alignment via Reward Function Optimization (NeurIPS 2023 · similarity 0.90)
- Redeeming intrinsic rewards via constrained optimization (NeurIPS 2022 · similarity 0.90)
- To the Max: Reinventing Reward in Reinforcement Learning (ICML 2024 · similarity 0.89)
- The Distributional Reward Critic Framework for Reinforcement Learning Under Perturbed Rewards (AAAI 2025 · similarity 0.89)
- Reward Shaping for Reinforcement Learning with An Assistant Reward Agent (ICML 2024 · similarity 0.88)
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.
