Suda Bharadwaj

Artificial Intelligence · 2020

A researcher in the Science corpus: 1 paper; trusts 1 researcher and is trusted by 0 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 6 citations into it

Whom Suda Bharadwaj trusts overall

Their strongest outbound trust, strongest first, inferred from their citations.

1. Sridhar Mahadevan
2. Christel Baier
3. Andrew Y. Ng

Papers from Suda Bharadwaj's perspective

Ordered by how strongly the researchers Suda Bharadwaj trusts endorse each paper. Same corpus, a different order for every researcher.

1. Policy Invariance Under Reward Transformations: Theory and Application to Reward Shaping
2. OpenAI Gym
3. Learning to Drive a Bicycle Using Reinforcement Learning and Shaping
4. A Reinforcement Learning Method for Maximizing Undiscounted Rewards
5. A survey of robot learning from demonstration
6. Principles of model checking
7. Reinforcement Learning with Human Teachers: Evidence of Feedback and Guidance with Implications for Learning Performance
8. Average reward reinforcement learning: Foundations, algorithms, and empirical results
9. Potential-Based Shaping and Q-Value Initialization are Equivalent
10. Interactively shaping agents via human reinforcement: the TAMER framework

Their papers

• Temporal-Logic-Based Reward Shaping for Continuing Reinforcement Learning Tasks (2020) — 57 citations