`

Timezone: »

 
Poster
MADE: Exploration via Maximizing Deviation from Explored Regions
Tianjun Zhang · Paria Rashidinejad · Jiantao Jiao · Yuandong Tian · Joseph Gonzalez · Stuart Russell

Tue Dec 07 04:30 PM -- 06:00 PM (PST) @ None #None

In online reinforcement learning (RL), efficient exploration remains particularly challenging in high-dimensional environments with sparse rewards. In low-dimensional environments, where tabular parameterization is possible, count-based upper confidence bound (UCB) exploration methods achieve minimax near-optimal rates. However, it remains unclear how to efficiently implement UCB in realistic RL tasks that involve non-linear function approximation. To address this, we propose a new exploration approach via maximizing the deviation of the occupancy of the next policy from the explored regions. We add this term as an adaptive regularizer to the standard RL objective to balance exploration vs. exploitation. We pair the new objective with a provably convergent algorithm, giving rise to a new intrinsic reward that adjusts existing bonuses. The proposed intrinsic reward is easy to implement and combine with other existing RL algorithms to conduct exploration. As a proof of concept, we evaluate the new intrinsic reward on tabular examples across a variety of model-based and model-free algorithms, showing improvements over count-only exploration strategies. When tested on navigation and locomotion tasks from MiniGrid and DeepMind Control Suite benchmarks, our approach significantly improves sample efficiency over state-of-the-art methods.

Author Information

Tianjun Zhang (University of California, Berkeley)
Paria Rashidinejad (University of California, Berkeley)
Jiantao Jiao (University of California, Berkeley)
Yuandong Tian (Facebook AI Research)
Joseph Gonzalez (UC Berkeley)
Stuart Russell (UC Berkeley)

More from the Same Authors