Reinforcement Learning
Planning with General Objective Functions: Going Beyond Total Rewards Ruosong Wang
This "small" difference requires the agent to change the planning strategy significantly because the
Unknown-Aware Domain Adversarial Learning for Open-Set Domain Adaptation
Open-Set Domain Adaptation (OSDA) assumes that a target domain contains unknown classes, which are not discovered in a source domain.
Deep Inverse Q-learning with Constraints Appendix Gabriel Kalweit
Visualizations of the real and learned state-values of IA VI, IQL and DIQL can be found in Figure 7.Figure 7: Visualization of state-values for different numbers of trajectories in Objectworld. Table 2: Comparison between online and offline estimation of state-action visitations for the Ob-jectworld environment, given a data set with an action distribution equivalent to the true optimal Boltzmann distribution. The pseudocode of the tabular variant of Constrained Inverse Q-learning can be found in Algorithm 4. See [4] for further details of Constrained Q-learning.Algorithm 4: Tabular Model-free Constrained Inverse Q-learning The pseudocode of Deep Constrained Inverse Q-learning can be found in Algorithm 5. The lower row shows the EVD. 3 For DIQL, the parameters were optimized in the range of Hence, it can only increase.
Deep Inverse Q-learning with Constraints
Popular Maximum Entropy Inverse Reinforcement Learning approaches require the computation of expected state visitation frequencies for the optimal policy under an estimate of the reward function.
Iterative Amortized Policy Optimization Joseph Marino
Given this perspective, we consider the more flexible class of iterative amortized optimizers.
Reinforcement Learning with State Observation Costs in Action-Contingent Noiselessly Observable Markov Decision Processes
One key difference between reinforcement learning in simulated vs. real-world environments is that, in most simulated environments, the agent can fully observe
An Equivalence between Loss Functions and Non-Uniform Sampling in Experience Replay
PER is intuitive, this commonly used technique lacks a critical theoretical foundation.
Multi-Agent Reinforcement Learning is A Sequence Modeling Problem
Our goal is to build the bridge between MARL and SMs so that the modeling power of modern sequence models can be unleashed for MARL.