agarwl

agarwl.github.io

Awesome-LLM-Long-Context-Modeling

📰 Must-read papers and blogs on LLM based Long Context Modeling 🔥

copy-on-write-xv6

Implementation of copy-on-write fork feature in xv6

Movie-Recommendation-Engine

CS 403/725 (Machine Learning) Project

neural_additive_models

Repo for open sourcing the NAMs.

pse

Website for "Contrastive Behavioral Similarity Embeddings for Generalization in Reinforcement Learning"

siamese-transfer-learning

batch_rl

Offline Reinforcement Learning (aka Batch Reinforcement Learning) on Atari 2600 games

reincarnating_rl

[NeurIPS 2022] Open source code for reusing prior computational work in RL.

rliable

[NeurIPS'21 Outstanding Paper] Library for reliable evaluation on RL and ML benchmarks, even with only a handful of seeds.

agarwl/neural_additive_models

Repo for open sourcing the NAMs.

agarwl/pse

Website for "Contrastive Behavioral Similarity Embeddings for Generalization in Reinforcement Learning"

agarwl/agarwl.github.io

agarwl/Awesome-LLM-Long-Context-Modeling

📰 Must-read papers and blogs on LLM based Long Context Modeling 🔥

agarwl/neural-symbolic-machines

Neural Symbolic Machines is a framework to integrate neural networks and symbolic representations using reinforcement learning, with applications in program synthesis and semantic parsing.

agarwl/neural_additive_models-1

stand alone Neural Additive Models, forked from google-reasearch for easy import to colab

agarwl/off_policy_mujoco

PyTorch implementation of BCQ for "Off-Policy Deep Reinforcement Learning without Exploration"

agarwl/iup

Webpage for Implicit Under-Parameterization Inhibits Data-Efficient Deep Reinforcement Learning

agarwl/rl_benchmark_scores

Raw scores for all papers for various benchmarks for reliable evaluation.

agarwl/google-research

Google Research

agarwl/reincarnating_rl

agarwl/rliable

agarwl/scala-open-letter.github.io

agarwl/spr

Code for "Data-Efficient Reinforcement Learning with Self-Predictive Representations"

agarwl/auto-drac

Automatic Data-Regularized Actor-Critic (Auto-DrAC)

agarwl/dopamine

Dopamine is a research framework for fast prototyping of reinforcement learning algorithms.

agarwl/github-buttons

Showcase the success of any GitHub repo or user with these simple, static buttons with dynamic counts.

agarwl/gym-minigrid

Minimalistic gridworld package for OpenAI Gym

agarwl/handful-of-trials

Experiment code for "Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models"

agarwl/interpret

Fit interpretable models. Explain blackbox machine learning.

agarwl/merl

Meta Reward Learning

agarwl/netrand

Network Randomization: A Simple Technique for Generalization in Deep Reinforcement Learning / ICLR 2020

agarwl/neural-additive-models.github.io

agarwl/offline-rl.github.io

agarwl/planet

Deep Planning Network: Control from pixels by latent planning with learned dynamics

agarwl/procgen

Procgen Benchmark: Procedurally-Generated Game-Like Gym-Environments

agarwl/python-bloom-filter

Bloom filter for Python

agarwl/reincarnating_rl_tmp

Open source code for reusing prior computational work in RL.

agarwl/shields

Concise, consistent, and legible badges in SVG and raster format

agarwl/tensorflow-value-iteration-networks

TensorFlow implementation of the Value Iteration Networks (NIPS '16) paper