Reinforcement Learning
Near-optimal Reinforcement Learning in Factored MDPs
Neural Information Processing Systems http://nips.cc/
Text-Based Interactive Recommendation via Constraint-Augmented Reinforcement Learning
Ruiyi Zhang, Tong Yu, Yilin Shen, Hongxia Jin, Changyou Chen
However, recommendations can easily violate preferences of users from their past natural-language feedback, since the recommender needs to explore new items for further improvement.
Policy Improvement via Imitation of Multiple Oracles
Despite its promise, reinforcement learning's real-world adoption has been hampered by the need for costly exploration to learn a good policy.
The V alue-Equivalence Principle for Model-Based Reinforcement Learning Supplementary Material
In this supplement we give details of our theoretical results and experiments that had to be left out of the main paper due to space constraints. Section A.1.1 contains derivations of the properties and propositions presented in the main Section A.2 provides a detailed outline of the pipeline used across our experiments in the The numbering of equations, figures and citations resume from what is used in the main paper. This result directly follows from Definitions 1 and 2.Property 2. M( null, V) either contains m We will show the result by contradiction. In order to prove Proposition 2 we will need four lemmas which we state and prove below. It follows that H - dim[B ] = nm rank(A) rank(C).
The Value Equivalence Principle for Model-Based Reinforcement Learning
Learning models of the environment from data is often viewed as an essential component to building intelligent reinforcement learning (RL) agents. The common practice is to separate the learning of the model from its use, by constructing a model of the environment's dynamics that correctly predicts the observed state transitions. In this paper we argue that the limited representational resources of model-based RL agents are better used to build models that are directly useful for value-based planning.
Planning in entropy-regularized Markov decision processes and games
Jean-Bastien Grill, Omar Darwiche Domingues, Pierre Menard, Remi Munos, Michal Valko
Planning with a generative model is thinking before acting .
Independent Policy Gradient Methods for Competitive Reinforcement Learning
These algorithms are typically employed in settings where the number of players and the type of interaction (competitive, cooperative, etc.) are both
Towards Optimal Off-Policy Evaluation for Reinforcement Learning with Marginalized Importance Sampling
Tengyang Xie, Yifei Ma, Yu-Xiang Wang
Solving OPE is often the starting point in many RL applications. To tackle the problem of OPE, the idea of importance sampling (IS) corrects the mismatch in the distributions under the behavior policy and target policy.
Budgeted Reinforcement Learning in Continuous State Space
So far, BMDPs could only be solved in the case of finite state spaces with known dynamics. This work extends the state-of-the-art to continuous spaces environments and unknown dynamics. We show that the solution to a BMDP is a fixed point of a novel Budgeted Bellman Optimality operator. This observation allows us to introduce natural extensions of Deep Reinforcement Learning algorithms to address large-scale BMDPs.