gkswamy98
PhD Student @ CMU RI. MS from Berkeley. Summers @google @MicrosoftResearch, @aurora-opensource, @NVIDIA, and @ SpaceX.
Pinned Repositories
cmu-10732-robustness-adaptivity-shift
Official repository for CMU Machine Learning Department's 10732: Robustness and Adaptivity in Shifting Environments
jaxirl
Contains JAX implementation of algorithms for inverse reinforcement learning
causal_il
Contains implementation of the DoubIL and ResiduIL algorithms from the ICML '22 paper Causal Imitation Learning under Temporally Correlated Noise.
dotfiles
some of my configs
fast_irl
Contains implementation of the FILTER algorithm for exponentially faster inverse reinforcement learning.
imessage-spam-detection
pillbox
Contains implementation of AdVIL, AdRIL, and DAeQuIL algorithms from the ICML '21 Paper Of Moments and Matching.
sequence_model_il
Contains sequence-model implementations of on and off-policy imitation learning algorithms for problems with unobserved contexts.
valuedice
Fork of ValueDICE code that supports discrete action spaces, pybullet, and is truly off-policy.
garage
⚡️ Shockingly fast imitation learning algorithms via combining online and offline data engines. ⚡️
gkswamy98's Repositories
gkswamy98/fast_irl
Contains implementation of the FILTER algorithm for exponentially faster inverse reinforcement learning.
gkswamy98/pillbox
Contains implementation of AdVIL, AdRIL, and DAeQuIL algorithms from the ICML '21 Paper Of Moments and Matching.
gkswamy98/dotfiles
some of my configs
gkswamy98/causal_il
Contains implementation of the DoubIL and ResiduIL algorithms from the ICML '22 paper Causal Imitation Learning under Temporally Correlated Noise.
gkswamy98/sequence_model_il
Contains sequence-model implementations of on and off-policy imitation learning algorithms for problems with unobserved contexts.
gkswamy98/valuedice
Fork of ValueDICE code that supports discrete action spaces, pybullet, and is truly off-policy.
gkswamy98/meta-rl-bci
meta learning + maxent deeprl for shared autonomy from eeg signals
gkswamy98/replay_est
Contains implementation of the replay estimation algorithm from "Minimax Optimal Online Imitation Learning via Replay Estimation."
gkswamy98/adversarial_rl
CS 294-131 Project, reimplementing https://arxiv.org/pdf/1702.02284.pdf.
gkswamy98/ViZDoom
Doom-based AI Research Platform for Reinforcement Learning from Raw Visual Information. :godmode:
gkswamy98/icl
gkswamy98/autosort
Human assisted few-shot object sorting
gkswamy98/baselines
OpenAI Baselines: high-quality implementations of reinforcement learning algorithms
gkswamy98/causil
gkswamy98/D4RL
A collection of reference environments for offline reinforcement learning
gkswamy98/DQfD
An implementation of Deep Q-Learning from Demonstrations (DQfD) for playing Atari 2600 video games
gkswamy98/filter
gkswamy98/gym-minigrid
Minimalistic gridworld package for OpenAI Gym
gkswamy98/hyper
gkswamy98/il_envs
gkswamy98/jaco_learning
Control, planning, and learning system for human-robot interaction with a JACO2 7DOF robotic arm.
gkswamy98/mjrl
Reinforcement learning algorithms for MuJoCo tasks
gkswamy98/mmil
Website for ICML'21 paper.
gkswamy98/mu4e-dashboard
A dashboard for mu4e (mu for emacs)
gkswamy98/replay
gkswamy98/sequil
gkswamy98/serializable
Utilities for creating serializable classes
gkswamy98/softlearning
Softlearning is a reinforcement learning framework for training maximum entropy policies in continuous domains. Includes the official implementation of the Soft Actor-Critic algorithm.
gkswamy98/spo
gkswamy98/valentinp.github.com
My public page.