Prabhat Nagarajan

icon indicating a website link prabhatnagarajan.com

icon company The University of Alberta icon location Edmonton, Canada icon location Reinforcement Learning PhD student at UAlberta

Results 17 issues of Prabhat Nagarajan

Add Support for Deepmind Lab

Deepmind Lab is becoming more frequently used in DRL research. We should try and add support for Deepmind Lab if possible.

enhancement

[WIP] Implements Hindsight Experience Replay

2 comment

Bootstrapped DQN

Add bootstrapped DQN to ChainerRL

enhancement

Adds Clearing of Replay Buffer

9 comment

Hindsight Experience Replay

5 comment

Hindsight Experience Replay with bit-flipping example: https://arxiv.org/abs/1707.01495

Hindsight Experience Replay Buffer

22 comment

Depends on https://github.com/pfnet/pfrl/pull/80. Resolves https://github.com/pfnet/pfrl/issues/6. Results: ![her_bit_flip_dqn](https://user-images.githubusercontent.com/10005453/97736859-a0c2f700-1b1f-11eb-85ce-5fcf8e69d4dd.png)

Make Recurrent DDPG

1 comment

DDPG does not support recurrence.

Support Environment Evaluation Statistics for Batch/Vector Environments

Try OpenAI VecEnv support instead of PFRL's VectorEnv

Migrates or remove tests with @pytest.mark.skip

Some tests still have `@pytest.mark.skip` annotation from pre-migration. These tests should be updated or removed.