Search Results for author:
Found 10 papers, 3 papers with code
Constraint-Generation Policy Optimization (CGPO): Nonlinear Programming for Policy Optimization in Mixed Discrete-Continuous MDPs
To achieve such results, CGPO proposes a bi-level mixed-integer nonlinear optimization framework for optimizing policies within defined expressivity classes (i. e. piecewise (non)-linear) and reduces it to an optimal constraint generation methodology that adversarially generates worst-case state trajectories.
Thompson Sampling for Parameterized Markov Decision Processes with Uninformative Actions
We study parameterized MDPs (PMDPs) in which the key parameters of interest are unknown and must be learned using Bayesian inference.
pyRDDLGym: From RDDL to Gym Environments
We present pyRDDLGym, a Python framework for auto-generation of OpenAI Gym environments from RDDL declerative description.
Conservative Bayesian Model-Based Value Expansion for Offline Policy Optimization
Offline reinforcement learning (RL) addresses the problem of learning a performant policy from a fixed batch of data collected by following some behavior policy.
RAPTOR: End-to-end Risk-Aware MDP Planning and Policy Learning by Backpropagation
The direct optimization of this empirical objective in an end-to-end manner is called the risk-averse straight-line plan, which commits to a sequence of actions in advance and can be sub-optimal in highly stochastic domains.
Risk-Aware Transfer in Reinforcement Learning using Successor Features
Sample efficiency and risk-awareness are central to the development of practical reinforcement learning (RL) for complex decision-making.
ε-BMC: A Bayesian Ensemble Approach to Epsilon-Greedy Exploration in Model-Free Reinforcement Learning
Resolving the exploration-exploitation trade-off remains a fundamental problem in the design and implementation of reinforcement learning (RL) algorithms.
Bayesian Experience Reuse for Learning from Multiple Demonstrators
We demonstrate the effectiveness of this approach for static optimization of smooth functions, and transfer learning in a high-dimensional supply chain problem with cost uncertainty.
Contextual Policy Transfer in Reinforcement Learning Domains via Deep Mixtures-of-Experts
In this paper, we assume knowledge of estimated source task dynamics and policies, and common sub-goals but different dynamics.
Reinforcement Learning with Multiple Experts: A Bayesian Model Combination Approach
Potential based reward shaping is a powerful technique for accelerating convergence of reinforcement learning algorithms.
