Research map / Reinforcement learning / Visual and representation RL
Outcome-Driven Reinforcement Learning via Variational Inference
Tim G. J. Rudner, Vitchyr H. Pong, Rowan Thomas McAllister, Yarin Gal, Sergey Levine
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 |
|---|---|---|---|
| Fix q_T to the prior (remove dynamic discount factor) (ablation) | ODAC · Fetch | final normalized distance (x100, lower is better): 19 -> 53 | Hurt |
| Fix q_T to the prior (remove dynamic discount factor) (ablation) | ODAC · Faucet | final normalized distance (x100, lower is better): 13 -> 37 | Hurt |
| Fix q_T to the prior (remove dynamic discount factor) (ablation) | ODAC · Window | final normalized distance (x100, lower is better): 5.4 -> 7.9 | Hurt |
| Fix q_T to the prior (remove dynamic discount factor) (ablation) | ODAC · Ant | final normalized distance (x100, lower is better): 9 -> 12 | Hurt |
| Fix q_T to the prior (remove dynamic discount factor) (ablation) | ODAC · 2D | final normalized distance (x100, lower is better): 1.7 -> 1.0 | No clear effect |
| Fix q_T to the prior (remove dynamic discount factor) (ablation) | ODAC · Push | final normalized distance (x100, lower is better): 35 -> 37 | No clear effect |
| Replace learned dynamics model with fixed-variance Laplace model (ablation) | ODAC · Fetch | final normalized distance (x100, lower is better): 19 -> 15 | No clear effect |
| Replace learned dynamics model with fixed-variance Laplace model (ablation) | ODAC · Ant | final normalized distance (x100, lower is better): 9 -> 11 | No clear effect |
| Replace learned dynamics model with fixed-variance Laplace model (ablation) | ODAC · Faucet | final normalized distance (x100, lower is better): 13 -> 15 | No clear effect |
| Fix both q_T and dynamics model (ablation) | ODAC · Fetch | final normalized distance (x100, lower is better): 19 -> 66 | Hurt |
| Fix both q_T and dynamics model (ablation) | ODAC · Faucet | final normalized distance (x100, lower is better): 13 -> 38 | Hurt |
| Use learned dynamics model for both rewards and model-based planning (ablation) | ODAC · six environments | final distance | Hurt |
Closest papers by meaning
- DUO: Diverse, Uncertain, On-Policy Query Generation and Selection for Reinforcement Learning from Human Feedback (AAAI 2025 · similarity 0.88)
- Inverting the Bellman Equation: From $Q$-Values to World Models (NeurIPS 2026 · similarity 0.87)
- Hindsight PRIORs for Reward Learning from Human Preferences (ICLR 2024 · similarity 0.87)
- Efficient Language-instructed Skill Acquisition via Reward-Policy Co-Evolution (AAAI 2025 · similarity 0.87)
- Reinforcement Learning with Lookahead Information (NeurIPS 2024 · similarity 0.87)
- Latent Safety-Constrained Policy Approach for Safe Offline Reinforcement Learning (ICLR 2025 · similarity 0.87)
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.
