Research map / Reinforcement learning / Policy gradient and actor-critic
A Distributional Perspective on Reinforcement Learning
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 |
|---|---|---|---|
| Model return distributions with C51 instead of learning only expected action values with DQN | DQN on Atari 2600 · Atari 2600 training games | game performance | Helped |
| Increase the number of atoms in the categorical return distribution (ablation) | Categorical DQN · Atari 2600 training games | game performance | Helped |
| Use the single-parameter Bernoulli algorithm instead of DQN (ablation) | Atari 2600 training games · Five training games | game performance: 3 games out of 5 | Mixed |
| Use C51 with distributional value learning rather than Double DQN | Atari 2600 · Atari 2600 games | evaluation score | Helped |
| Use distributional value learning | Atari 2600 sparse-reward games · Venture and Private Eye | game performance | Helped |
Closest papers by meaning
- Action Gaps and Advantages in Continuous-Time Distributional Reinforcement Learning (NeurIPS 2024 · similarity 0.89)
- The Distributional Reward Critic Framework for Reinforcement Learning Under Perturbed Rewards (AAAI 2025 · similarity 0.89)
- A Distributional Analogue to the Successor Representation (ICML 2024 · similarity 0.89)
- Bellman Unbiasedness: Toward Provably Efficient Distributional Reinforcement Learning with General Value Function Approximation (ICML 2025 · similarity 0.88)
- Intrinsic Benefits of Categorical Distributional Loss: Uncertainty-aware Regularized Exploration in Reinforcement Learning (NeurIPS 2025 · similarity 0.88)
- A Principled Path to Fitted Distributional Evaluation (NeurIPS 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.