Timezone: »
Social
Continuing (Non-episodic) RL Problems
Yi Wan
Tue Jul 20 05:00 PM -- 06:00 PM & Thu Jul 22 07:00 AM -- 08:00 AM (PDT) @
Please join us if you are interested in continuing reinforcement learning problems where the agent has a single non-episodic stream of experience. In many cases, and most importantly for natural intelligence, the agent is never reset to a state that it has visited before. What is the right objective for these problems? How is the problem different from the episodic ones? Plz join this social if you are also curious about these questions!
Author Information
Yi Wan (University of Alberta)
More from the Same Authors
-
2022 Poster: Towards Evaluating Adaptivity of Model-Based Reinforcement Learning Methods »
Yi Wan · Ali Rahimi-Kalahroudi · Janarthanan Rajendran · Ida Momennejad · Sarath Chandar · Harm van Seijen -
2022 Spotlight: Towards Evaluating Adaptivity of Model-Based Reinforcement Learning Methods »
Yi Wan · Ali Rahimi-Kalahroudi · Janarthanan Rajendran · Ida Momennejad · Sarath Chandar · Harm van Seijen -
2022 Social: Designing an RL system toward AGI »
Yi Wan · Alex Ayoub -
2021 Poster: Average-Reward Off-Policy Policy Evaluation with Function Approximation »
Shangtong Zhang · Yi Wan · Richard Sutton · Shimon Whiteson -
2021 Spotlight: Average-Reward Off-Policy Policy Evaluation with Function Approximation »
Shangtong Zhang · Yi Wan · Richard Sutton · Shimon Whiteson -
2021 Poster: Learning and Planning in Average-Reward Markov Decision Processes »
Yi Wan · Abhishek Naik · Richard Sutton -
2021 Spotlight: Learning and Planning in Average-Reward Markov Decision Processes »
Yi Wan · Abhishek Naik · Richard Sutton