Search Results for author:
Found 6 papers, 2 papers with code
Estimating Q(s,s') with Deep Deterministic Dynamics Gradients
In this paper, we introduce a novel form of value function, $Q(s, s')$, that expresses the utility of transitioning from a state $s$ to a neighboring state $s'$ and then acting optimally thereafter.
Perceptual Values from Observation
Imitation by observation is an approach for learning from expert demonstrations that lack action information, such as videos.
Imitating Latent Policies from Observation
In this paper, we describe a novel approach to imitation learning that infers latent policies directly from state observations.
Forward-Backward Reinforcement Learning
If we relax this one restriction and endow the agent with knowledge of the reward function, and in particular of the goal, we can leverage backwards induction to accelerate training.
Transferring Agent Behaviors from Videos via Motion GANs
A major bottleneck for developing general reinforcement learning agents is determining rewards that will yield desirable behaviors under various circumstances.
General Reinforcement Learning
Generative Adversarial Network
+2
Cross-Domain Perceptual Reward Functions
One problem with this approach is that we typically need to redefine the rewards each time the goal changes, which often requires some understanding of the solution in the agents environment.
