Research map / Reinforcement learning / Policy gradient and actor-critic
Maximum Entropy RL (Provably) Solves Some Robust RL Problems
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 MaxEnt RL with the pessimistic reward incorporating log reward and dynamics entropy | MaxEnt RL · Robust RL under dynamics perturbations | lower bound on robust objective | Helped |
| Use MaxEnt RL rather than standard RL | Pusher with a new obstacle · Pusher | robust task performance | Helped |
| Use MaxEnt RL rather than standard RL | Button task with moved goal · Button | robust task performance | Helped |
| Use a larger entropy coefficient (ablation) | MaxEnt RL on the pusher task · Mid-episode puck-position perturbations | robust performance | Helped |
| Use MaxEnt RL rather than standard RL | Peg insertion · Adversarial hole-location perturbations | success rate | Helped |
| Add independent Gaussian action noise to the standard RL policy (ablation) | Standard RL on 2D navigation · Navigation with a new L-shaped obstacle | task performance | Mixed |
| Use MaxEnt RL rather than standard RL | Policies evaluated on adversarially chosen reward functions · Four OpenAI Gym continuous-control tasks | worst-case cumulative reward | Helped |
| Use a large entropy coefficient rather than a small one (ablation) | MaxEnt RL · Mass-variation benchmark tasks | robust performance | Helped |
| Use MaxEnt RL with a large entropy coefficient rather than small entropy coefficients (ablation) | MaxEnt RL · Pusher with mid-episode disturbances | robustness to larger disturbances | Helped |
Closest papers by meaning
- When Maximum Entropy Misleads Policy Optimization (ICML 2025 · similarity 0.92)
- Robust Reinforcement Learning with General Utility (NeurIPS 2024 · similarity 0.90)
- State Entropy Regularization for Robust Reinforcement Learning (NeurIPS 2025 · similarity 0.89)
- Robust Gymnasium: A Unified Modular Benchmark for Robust Reinforcement Learning (ICLR 2025 · similarity 0.89)
- Minimax Optimal and Computationally Efficient Algorithms for Distributionally Robust Offline Reinforcement Learning (NeurIPS 2024 · similarity 0.88)
- Model-based RL as a Minimalist Approach to Horizon-Free and Second-Order Bounds (ICLR 2025 · 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.