02/02/2021

Mean-Variance Policy Iteration for Risk-Averse Reinforcement Learning

Shangtong Zhang, Bo Liu, Shimon Whiteson

Keywords:

Abstract Paper Similar Papers

Abstract: We present a mean-variance policy iteration (MVPI) framework for risk-averse control in a discounted infinite horizon MDP optimizing the variance of a per-step reward random variable. MVPI enjoys great flexibility in that any policy evaluation method and risk-neutral control method can be dropped in for risk-averse control off the shelf, in both on- and off-policy settings. This flexibility reduces the gap between risk-neutral control and risk-averse control and is achieved by working on a novel augmented MDP directly. We propose risk-averse TD3 as an example instantiating MVPI, which outperforms vanilla TD3 and many previous risk-averse control methods in challenging Mujoco robot simulation tasks under a risk-aware performance metric. This risk-averse TD3 is the first to introduce deterministic policies and off-policy learning into risk-averse reinforcement learning, both of which are key to the performance boost we show in Mujoco domains.

The video of this talk cannot be embedded. You can watch it here:
https://slideslive.com/38949046
(Link will open in new window)
 0
 0
 0
 0
  Share    
This is an embedded video. Talk and the respective paper are published at AAAI 2021 virtual conference. If you are one of the authors of the paper and want to manage your upload, see the question "My papertalk has been externally embedded..." in the FAQ section.

Comments

Post Comment
no comments yet
code of conduct: tbd Characters remaining: 140

Similar Papers

 1
 0
 0
 0
 13:54 
 0
 0
 0
 0
 3:22 
 1
 0
 0
 0
 3:50 
 0
 0
 0
 0
 1:01 
 0
 0
 0
 0
 14:29 
 0
 0
 0
 0
 5:07 
 0
 0
 0
 0
 5:24 
 0
 0
 0
 0
 14:40 
 0
 0
 0
 0
 4:49 
 0
 0
 0
 0
 5:05 
 0
 0
 0
 0
 5:14 
 0
 0
 0
 0
 5:00 
 0
 0
 0
 0
 5:04 
 0
 0
 0
 0
 14:35 
 0
 0
 0
 0
 9:40 
 0
 0
 0
 0
 3:19 
 0
 0
 0
 0
 5:04 
 0
 0
 0
 0
 14:13 
 0
 0
 0
 0
 13:14 
 0
 0
 0
 0
 13:50 
 0
 0
 0
 0
 3:11 
 0
 0
 0
 1
 10:04 
 0
 0
 0
 0
 11:44 
 0
 0
 0
 0
 4:28 
 0
 0
 0
 0
 5:18 
 0
 0
 0
 0
 15:45 
 0
 0
 0
 0
 6:30 
 0
 0
 0
 0
 5:19 
 0
 0
 0
 0
 12:04 
 0
 0
 0
 0
 1:00 
 0
 0
 0
 0
 4:55 
 0
 0
 0
 0
 3:15 
 0
 0
 0
 0
 5:43 
 0
 0
 0
 0
 13:11 
 0
 0
 0
 0
 11:12 
 0
 0
 0
 0
 16:03 
 0
 0
 0
 0
 12:25 
 0
 0
 0
 0
 3:07 
 0
 0
 0
 0
 6:48 
 0
 0
 0
 0
 10:49