DropoutDAgger google
While imitation learning is becoming common practice in robotics, this approach often suffers from data mismatch and compounding errors. DAgger is an iterative algorithm that addresses these issues by continually aggregating training data from both the expert and novice policies, but does not consider the impact of safety. We present a probabilistic extension to DAgger, which uses the distribution over actions provided by the novice policy, for a given observation. Our method, which we call DropoutDAgger, uses dropout to train the novice as a Bayesian neural network that provides insight to its confidence. Using the distribution over the novice’s actions, we estimate a probabilistic measure of safety with respect to the expert action, tuned to balance exploration and exploitation. The utility of this approach is evaluated on the MuJoCo HalfCheetah and in a simple driving experiment, demonstrating improved performance and safety compared to other DAgger variants and classic imitation learning. …

Conflict-Driven Clause Learning (CDCL) google
In computer science, Conflict-Driven Clause Learning (CDCL) is an algorithm for solving the Boolean satisfiability problem (SAT). Given a Boolean formula, the SAT problem asks for an assignment of variables so that the entire formula evaluates to true. The internal workings of CDCL SAT solvers were inspired by DPLL solvers. …

Nested LSTM (NLSTM) google
We propose Nested LSTMs (NLSTM), a novel RNN architecture with multiple levels of memory. Nested LSTMs add depth to LSTMs via nesting as opposed to stacking. The value of a memory cell in an NLSTM is computed by an LSTM cell, which has its own inner memory cell. Specifically, instead of computing the value of the (outer) memory cell as $c^{outer}_t = f_t \odot c_{t-1} + i_t \odot g_t$, NLSTM memory cells use the concatenation $(f_t \odot c_{t-1}, i_t \odot g_t)$ as input to an inner LSTM (or NLSTM) memory cell, and set $c^{outer}_t$ = $h^{inner}_t$. Nested LSTMs outperform both stacked and single-layer LSTMs with similar numbers of parameters in our experiments on various character-level language modeling tasks, and the inner memories of an LSTM learn longer term dependencies compared with the higher-level units of a stacked LSTM. …

Advertisements