Heinrich Küttler

reinforcement learning (2) imitation learning (1) curriculum learning (1) sequential decision making (1) question answering (1) covariate shift (1) minimax regret (1) retrieval-augmented generation (1) language generation (1) unsupervised environment design (1) aleatoric uncertainty (1) knowledge-intensive task (1) trajectory learning (1) seq2seq model (1) procedurally generated environment (1) large language model (1) skill acquisition (1) language-conditioned reinforcement learning (1) dense vector retrieval (1)