15 Inverse Reinforcement Learning

Deep Reinforcement Learning

Overview
1 Basics
2 Deep learning
3 Value-based methods
4 Policy Gradient methods
5 Advantage Actor-Critic methods
6 Off-policy Actor-Critic
7 Deterministic Policy Gradient (DPG)
8 Natural Gradients
9 Maximum Entropy RL
10 Distributional learning
11 Miscellaneous model-free algorithm
12 Recurrent Attention Models
13 Model-based RL
14 Hierarchical Reinforcement Learning
15 Inverse Reinforcement Learning
16 Deep RL for robotics
17 Deep RL in practice
References

15 Inverse Reinforcement Learning

work in progress

Hindsight experience replay: Andrychowicz et al. (2017)

Goal-conditioned inverse RL: Ding et al. (2019)

Andrychowicz, M., Wolski, F., Ray, A., Schneider, J., Fong, R., Welinder, P., et al. (2017). Hindsight Experience Replay. Available at: http://arxiv.org/abs/1707.01495.

Ding, Y., Florensa, C., Phielipp, M., and Abbeel, P. (2019). Goal-conditioned Imitation Learning. in (Long Beach, California: PMLR), 8. Available at: https://openreview.net/pdf?id=HkglHcSj2N.

14 Hierarchical Reinforcement Learning

16 Deep RL for robotics