Rahul V. Kulkarni

Reinforcement Learning (1)

entropy regularization (3) value function (2) optimal policy (2) reward shaping (2) reinforcement learning (2) soft value function (1) entropy-regularized reinforcement learning (1) task composition (1) potential-based reward shaping (1) state-value function (1) compositional framework (1) value function bound (1) zero-shot policy (1) bayesian inference (1) regret bound (1) sparse reward (1) stochastic dynamics (1)