Dharshan Kumaran
Source-listed: Google DeepMind
Record snapshot: Sep 3, 2026. Coverage and affiliations may be incomplete or historical.
Selected work
5- Competing Biases underlie Overconfidence and Underconfidence in LLMsSaved credit: Contributor · 2026Explore people connected to this work →
- Transformers need glasses! Information over-squashing in language tasksSaved credit: Contributor · 2024Explore people connected to this work →
- A general reinforcement learning algorithm that masters chess, shogi, and Go through self-playSaved credit: Contributor · 2018Explore people connected to this work →
- Vector-based navigation using grid-like representations in artificial agentsSaved credit: Contributor · 2018Explore people connected to this work →
- Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning AlgorithmSaved credit: Contributor · 2017Explore people connected to this work →