Research map / Reinforcement learning / Visual and representation RL
How Should an Agent Practice?
Janarthanan Rajendran, Richard Lewis, Vivek Veeriah, Honglak Lee, 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 practice periods with meta-gradient-learned practice rewards | A2C · Pong | mean reward | Improved |
| Add practice periods with meta-gradient-learned practice rewards | A2C · PacMan | mean reward | Improved |
| Replace meta-gradient reward learning with a fixed random practice reward (ablation) | A2C + Meta-Gradients Practice · Pong | mean reward | Hurt |
| Replace meta-gradient reward learning with a fixed random practice reward (ablation) | A2C + Meta-Gradients Practice · PacMan | mean reward | Hurt |
| Replace meta-gradient-learned rewards with match-reward prediction | A2C + Meta-Gradients Practice · Pong | mean reward | Hurt |
| Replace meta-gradient-learned rewards with match-reward prediction | A2C + Meta-Gradients Practice · PacMan | mean reward | Mixed |
| Use practice time for meta-gradient-guided practice instead of additional matches | A2C · Pong | mean reward | Improved |
| Use practice time for practice without ghosts instead of additional matches | A2C · PacMan | mean reward | Hurt |
| Add match-reward training after practice updates to adapt the intrinsic practice reward | REINFORCE · Corridor world | reward per episode | Improved |
Closest papers by meaning
- A Single Goal is All You Need: Skills and Exploration Emerge from Contrastive RL without Rewards, Demonstrations, or Subgoals (ICLR 2025 · similarity 0.86)
- First-Explore, then Exploit: Meta-Learning to Solve Hard Exploration-Exploitation Trade-Offs (NeurIPS 2024 · similarity 0.85)
- When Do Skills Help Reinforcement Learning? A Theoretical Analysis of Temporal Abstractions (ICML 2024 · similarity 0.85)
- From Raw Experience to Skill Consumption: A Systematic Study of Model-Generated Agent Skills (NeurIPS 2026 · similarity 0.84)
- The Indoor-Training Effect: Unexpected Gains from Distribution Shifts in the Transition Function (AAAI 2025 · similarity 0.84)
- Individual Contributions as Intrinsic Exploration Scaffolds for Multi-agent Reinforcement Learning (ICML 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.
