issues
search
HumanCompatibleAI
/
adversarial-policies
Find best-response to a fixed policy in multi-agent RL
MIT License
275
stars
47
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
Noisy Actions & Noise-Masked Observations
#14
decodyng
closed
5 years ago
1
Observation Masking
#13
AdamGleave
closed
5 years ago
1
t-SNE visualization
#12
AdamGleave
closed
5 years ago
3
Generate videos for experiments
#11
AdamGleave
closed
5 years ago
2
Lookback
#10
kantneel
closed
5 years ago
2
Modifications to VideoWrapper Video Storage
#9
decodyng
closed
5 years ago
3
Functionality for GAIL
#8
kantneel
closed
5 years ago
5
"Transparent" policies and VecEnv.
#7
kantneel
closed
5 years ago
9
Add support to fine-tune policies from gym_compete
#6
AdamGleave
closed
5 years ago
2
Checkpointing support with ray Tune
#5
AdamGleave
opened
5 years ago
1
Integrating features
#4
kantneel
closed
5 years ago
1
Fix SubprocVecEnv related hang
#3
AdamGleave
closed
5 years ago
1
Merging work on reward shaping and annealing
#2
kantneel
closed
5 years ago
2
Make Docker image smaller
#1
AdamGleave
closed
4 years ago
0
Previous