My interests include representation learning, structure discovery, generative probabilistic models, switching state-space models, Bayesian non-parametric learning of disease phenotypes, and, more recently, off-policy reinforcement learning and causal inference.
The output synchronization problem is then formulated as an optimal control problem and a novel model-free off-policy reinforcement learning algorithm is developed to solve the optimal output synchronization problem online in real time.
The optical flow algorithm's gains are further tuned using policy gradient reinforcement learning so as to improve motion estimation for specific unsteady regimes.
In this paper, we present a method for concurrent learning of best strategy and optimal parameters using policy gradient reinforcement learning algorithm.
This paper proposes a method for designing 'intrinsic' rewards of autonomous agents by combining constrained policy gradient reinforcement learning and embodied evolution.
Appropriately designing sampling policies is highly important for obtaining better control policies in reinforcement learning.
Second, I exhibit a framework for utilizing textual descriptions to tackle the challenging problem of cross-domain policy transfer for reinforcement learning (RL).
Objectives – The authors wanted to assess the impact of an "isolation" reinforcement policy in a French general hospital intensive care unit (ICU), between 1994 and 1999.
Using these techniques requires a deviation from the Partially Observable Markov Decision Processes (POMDP) and some innovations: heuristic techniques for generalizing the experience and for treating the partial observability; a technique for the speed adjournment of the Q function; the definition of a special reinforcement policy adequate for learning a complex task without supervision.
So, this executive order is less a change in policy than a reinforcement of a longstanding history of behavioral science for government decision making.
